Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.8034. Min Act: -0.1700
Data Index: 2872787 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.7096. Min Act: -0.1700
Data Index: 1636292 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.7096. Min Act: -0.1700
Data Index: 4634307 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.7096. Min Act: -0.1700
Data Index: 4312829 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.7096. Min Act: -0.1700
Data Index: 1333161 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6471. Min Act: -0.1700
Data Index: 7337493 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6471. Min Act: -0.1700
Data Index: 101161 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6784. Min Act: -0.1700
Data Index: 5545347 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6784. Min Act: -0.1700
Data Index: 2250438 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6471. Min Act: -0.1700
Data Index: 3118285 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6159. Min Act: -0.1700
Data Index: 5179271 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6471. Min Act: -0.1700
Data Index: 1756053 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6471. Min Act: -0.1700
Data Index: 6733198 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6159. Min Act: -0.1700
Data Index: 4178022 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6471. Min Act: -0.1700
Data Index: 5285755 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6159. Min Act: -0.1699
Data Index: 445886 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.5846. Min Act: -0.1700
Data Index: 3851297 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.5846. Min Act: -0.1700
Data Index: 199242 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.5846. Min Act: -0.1700
Data Index: 3130974 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8034. Min Range: -4.8034
Max Act: 4.6159. Min Act: -0.1699
Data Index: 829538 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19