Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1311 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.6506. Min Act: -0.1541
Data Index: 8605236 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.6187. Min Act: -0.1683
Data Index: 5425726 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.6187. Min Act: -0.1644
Data Index: 4943070 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5793. Min Act: -0.1689
Data Index: 1251183 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5638. Min Act: -0.1669
Data Index: 6830620 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5483. Min Act: -0.1697
Data Index: 7830997 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5483. Min Act: -0.1700
Data Index: 2301439 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5407. Min Act: -0.1700
Data Index: 4604273 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5407. Min Act: -0.1624
Data Index: 7767874 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5330. Min Act: -0.1684
Data Index: 6587246 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5330. Min Act: -0.1459
Data Index: 468280 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5254. Min Act: -0.1578
Data Index: 5410656 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5254. Min Act: -0.1671
Data Index: 5031852 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5178. Min Act: -0.1700
Data Index: 4699586 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5178. Min Act: -0.1700
Data Index: 591424 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5178. Min Act: -0.1691
Data Index: 3448294 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.5102. Min Act: -0.1700
Data Index: 4264856 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.4877. Min Act: -0.1699
Data Index: 2165066 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.4655. Min Act: -0.1674
Data Index: 7948386 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6506. Min Range: -0.6506
Max Act: 0.4803. Min Act: -0.1696
Data Index: 3011038 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19