Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.5159. Min Act: -0.1700
Data Index: 7948719 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.5159. Min Act: -0.1700
Data Index: 4347411 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.3909. Min Act: -0.1700
Data Index: 7045716 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.3597. Min Act: -0.1700
Data Index: 3805282 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.2659. Min Act: -0.1700
Data Index: 7490718 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.2659. Min Act: -0.1700
Data Index: 5082268 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.2972. Min Act: -0.1700
Data Index: 5618907 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.2347. Min Act: -0.1700
Data Index: 1780371 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.2034. Min Act: -0.1700
Data Index: 1317847 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.2034. Min Act: -0.1700
Data Index: 4983000 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1722. Min Act: -0.1700
Data Index: 2400346 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1409. Min Act: -0.1700
Data Index: 3543385 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1097. Min Act: -0.1700
Data Index: 1195594 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1409. Min Act: -0.1700
Data Index: 1122105 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1409. Min Act: -0.1700
Data Index: 7738679 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1409. Min Act: -0.1700
Data Index: 3804936 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1097. Min Act: -0.1700
Data Index: 5937671 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.1097. Min Act: -0.1700
Data Index: 6954027 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.0784. Min Act: -0.1700
Data Index: 445993 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5159. Min Range: -5.5159
Max Act: 5.0784. Min Act: -0.1700
Data Index: 1581089 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19