Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8496. Min Act: -0.1700
Data Index: 8134979 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8178. Min Act: -0.1700
Data Index: 1672091 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8178. Min Act: -0.1700
Data Index: 941199 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8178. Min Act: -0.1700
Data Index: 2812325 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8178. Min Act: -0.1700
Data Index: 7577232 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8019. Min Act: -0.1700
Data Index: 7659278 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.8178. Min Act: -0.1700
Data Index: 6392457 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7860. Min Act: -0.1700
Data Index: 4557891 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7701. Min Act: -0.1700
Data Index: 3371031 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7701. Min Act: -0.1700
Data Index: 3129475 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7701. Min Act: -0.1700
Data Index: 5356236 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7222. Min Act: -0.1700
Data Index: 8454456 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7222. Min Act: -0.1700
Data Index: 3615718 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7222. Min Act: -0.1700
Data Index: 3585171 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7222. Min Act: -0.1700
Data Index: 5792757 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7222. Min Act: -0.1700
Data Index: 5433811 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7222. Min Act: -0.1700
Data Index: 1576312 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7062. Min Act: -0.1700
Data Index: 234717 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.7062. Min Act: -0.1700
Data Index: 1939206 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8496. Min Range: -2.8496
Max Act: 2.6581. Min Act: -0.1700
Data Index: 1010153 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19