Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.9429. Min Act: -0.1700
Data Index: 5716572 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.8804. Min Act: -0.1700
Data Index: 3487734 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.8804. Min Act: -0.1700
Data Index: 5936398 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.8179. Min Act: -0.1700
Data Index: 2663337 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.8179. Min Act: -0.1700
Data Index: 544497 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.7554. Min Act: -0.1700
Data Index: 1996439 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.7554. Min Act: -0.1700
Data Index: 699299 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.6929. Min Act: -0.1700
Data Index: 3217035 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.5679. Min Act: -0.1700
Data Index: 350920 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.5679. Min Act: -0.1700
Data Index: 2368434 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.6304. Min Act: -0.1700
Data Index: 6406577 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.5054. Min Act: -0.1700
Data Index: 4849928 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.5054. Min Act: -0.1700
Data Index: 8209687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.5054. Min Act: -0.1700
Data Index: 6948430 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.5054. Min Act: -0.1700
Data Index: 4298411 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.4429. Min Act: -0.1700
Data Index: 3966492 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.4429. Min Act: -0.1700
Data Index: 4307146 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.4429. Min Act: -0.1700
Data Index: 3495812 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.3804. Min Act: -0.1700
Data Index: 3020703 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9429. Min Range: -10.9429
Max Act: 10.3179. Min Act: -0.1700
Data Index: 6371705 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19