Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.4222. Min Act: -0.1700
Data Index: 6684704 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.2659. Min Act: -0.1700
Data Index: 7270559 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.2659. Min Act: -0.1700
Data Index: 3951721 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.2347. Min Act: -0.1700
Data Index: 1616294 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.2034. Min Act: -0.1700
Data Index: 4573268 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.2034. Min Act: -0.1700
Data Index: 2566704 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1722. Min Act: -0.1700
Data Index: 7471748 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1722. Min Act: -0.1699
Data Index: 2566703 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1722. Min Act: -0.1700
Data Index: 669717 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1722. Min Act: -0.1700
Data Index: 1809396 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1722. Min Act: -0.1699
Data Index: 1285635 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1409. Min Act: -0.1700
Data Index: 5723960 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1409. Min Act: -0.1700
Data Index: 4472 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1409. Min Act: -0.1700
Data Index: 2499226 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1409. Min Act: -0.1700
Data Index: 5321793 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1097. Min Act: -0.1700
Data Index: 3419665 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1409. Min Act: -0.1700
Data Index: 527369 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1097. Min Act: -0.1700
Data Index: 5347371 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1097. Min Act: -0.1700
Data Index: 20078 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4222. Min Range: -6.4222
Max Act: 6.1097. Min Act: -0.1700
Data Index: 896880 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19