Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2253 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1402. Min Range: -6.1402
Max Act: 6.1402. Min Act: -0.1700
Data Index: 1046483 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.7340. Min Act: -0.1700
Data Index: 629295 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.7027. Min Act: -0.1700
Data Index: 4797953 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.6715. Min Act: -0.1700
Data Index: 483509 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.7027. Min Act: -0.1700
Data Index: 1175043 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.6090. Min Act: -0.1700
Data Index: 2034839 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.5777. Min Act: -0.1700
Data Index: 762250 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.5777. Min Act: -0.1700
Data Index: 1988167 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.5777. Min Act: -0.1700
Data Index: 6388822 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.5465. Min Act: -0.1700
Data Index: 7340326 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.5465. Min Act: -0.1700
Data Index: 2096812 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.5152. Min Act: -0.1700
Data Index: 1376037 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4840. Min Act: -0.1700
Data Index: 4708836 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4840. Min Act: -0.1700
Data Index: 8107589 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4840. Min Act: -0.1700
Data Index: 5567627 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4840. Min Act: -0.1700
Data Index: 697422 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4215. Min Act: -0.1700
Data Index: 643414 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4527. Min Act: -0.1700
Data Index: 3140692 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4215. Min Act: -0.1700
Data Index: 2349692 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1402. Min Range: -6.1402
Max Act: 5.4215. Min Act: -0.1700
Data Index: 6777978 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19