Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1493 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.1192. Min Act: -0.1700
Data Index: 2685895 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.1192. Min Act: -0.1700
Data Index: 7523950 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0879. Min Act: -0.1700
Data Index: 7717916 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0879. Min Act: -0.1700
Data Index: 5480933 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0879. Min Act: -0.1700
Data Index: 8471077 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0879. Min Act: -0.1700
Data Index: 6440865 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0566. Min Act: -0.1700
Data Index: 6404652 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0566. Min Act: -0.1700
Data Index: 8591042 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0254. Min Act: -0.1700
Data Index: 422039 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0254. Min Act: -0.1700
Data Index: 834630 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0254. Min Act: -0.1700
Data Index: 1248750 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0566. Min Act: -0.1700
Data Index: 2602608 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1192. Min Range: -4.1192
Max Act: 4.0254. Min Act: -0.1700
Data Index: 3246942 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 2284775 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 2758739 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 3647053 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 6011123 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 7580971 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 7643657 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1192. Min Range: -4.1192
Max Act: 3.9941. Min Act: -0.1700
Data Index: 3123195 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19