Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 21.9032. Min Range: -21.9032
Max Act: 21.9032. Min Act: -0.1700
Data Index: 7980178 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.9032. Min Range: -21.9032
Max Act: 21.4032. Min Act: -0.1700
Data Index: 5765591 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.9032. Min Range: -21.9032
Max Act: 21.2782. Min Act: -0.1700
Data Index: 2952666 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.9032. Min Range: -21.9032
Max Act: 21.2782. Min Act: -0.1700
Data Index: 8209697 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.9032. Min Range: -21.9032
Max Act: 21.1532. Min Act: -0.1700
Data Index: 5830711 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.9032. Min Range: -21.9032
Max Act: 21.1532. Min Act: -0.1700
Data Index: 6369835 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.6532. Min Act: -0.1700
Data Index: 3284668 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.7782. Min Act: -0.1700
Data Index: 372215 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.5282. Min Act: -0.1700
Data Index: 6466327 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.6532. Min Act: -0.1700
Data Index: 2952668 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.7782. Min Act: -0.1700
Data Index: 5960453 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.6532. Min Act: -0.1700
Data Index: 5960452 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.6532. Min Act: -0.1700
Data Index: 3044728 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.6532. Min Act: -0.1700
Data Index: 8209699 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.7782. Min Act: -0.1700
Data Index: 6267422 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.5282. Min Act: -0.1700
Data Index: 6892458 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.5282. Min Act: -0.1700
Data Index: 2341980 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.5282. Min Act: -0.1700
Data Index: 3284667 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.4032. Min Act: -0.1700
Data Index: 6224741 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.9032. Min Range: -21.9032
Max Act: 20.4032. Min Act: -0.1700
Data Index: 5830713 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19