Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6369. Min Range: -6.6369
Max Act: 6.6369. Min Act: -0.1700
Data Index: 3573633 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6369. Min Range: -6.6369
Max Act: 6.1994. Min Act: -0.1700
Data Index: 7173641 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6369. Min Range: -6.6369
Max Act: 6.1369. Min Act: -0.1700
Data Index: 3615185 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6369. Min Range: -6.6369
Max Act: 6.1369. Min Act: -0.1700
Data Index: 6413935 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6369. Min Range: -6.6369
Max Act: 6.1369. Min Act: -0.1700
Data Index: 3033027 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6369. Min Range: -6.6369
Max Act: 6.0432. Min Act: -0.1700
Data Index: 7397243 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9494. Min Act: -0.1700
Data Index: 7906878 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9807. Min Act: -0.1700
Data Index: 286283 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9182. Min Act: -0.1700
Data Index: 4864561 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9182. Min Act: -0.1700
Data Index: 6111458 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9182. Min Act: -0.1700
Data Index: 5500646 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9182. Min Act: -0.1700
Data Index: 5599887 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8869. Min Act: -0.1700
Data Index: 7887429 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.9182. Min Act: -0.1700
Data Index: 2195993 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8869. Min Act: -0.1700
Data Index: 5367665 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8557. Min Act: -0.1700
Data Index: 178925 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8557. Min Act: -0.1700
Data Index: 566426 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8557. Min Act: -0.1700
Data Index: 7629423 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2105766 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6369. Min Range: -6.6369
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3054779 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19