Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.6282. Min Act: -0.1700
Data Index: 7559508 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.5657. Min Act: -0.1700
Data Index: 2013970 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.5032. Min Act: -0.1700
Data Index: 2722376 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.4094. Min Act: -0.1700
Data Index: 2618693 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3782. Min Act: -0.1700
Data Index: 6079902 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.4094. Min Act: -0.1700
Data Index: 6946564 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3469. Min Act: -0.1700
Data Index: 4794423 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3782. Min Act: -0.1700
Data Index: 4692889 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3469. Min Act: -0.1700
Data Index: 1731051 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3157. Min Act: -0.1700
Data Index: 8346849 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3157. Min Act: -0.1700
Data Index: 8762465 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3157. Min Act: -0.1700
Data Index: 720969 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3157. Min Act: -0.1700
Data Index: 5516809 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.3157. Min Act: -0.1700
Data Index: 8042870 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.2844. Min Act: -0.1700
Data Index: 262189 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.2844. Min Act: -0.1700
Data Index: 6737756 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.2844. Min Act: -0.1700
Data Index: 5517919 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.2532. Min Act: -0.1700
Data Index: 5221966 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.2532. Min Act: -0.1700
Data Index: 5968350 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6282. Min Range: -4.6282
Max Act: 4.2219. Min Act: -0.1700
Data Index: 1512509 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19