Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.9767. Min Act: -0.1571
Data Index: 355093 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8917. Min Act: -0.1498
Data Index: 2695499 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8490. Min Act: -0.1684
Data Index: 8473306 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8490. Min Act: -0.1692
Data Index: 2397594 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8318. Min Act: -0.1498
Data Index: 6058026 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8233. Min Act: -0.1694
Data Index: 573666 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8233. Min Act: -0.1700
Data Index: 4755587 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8233. Min Act: -0.1698
Data Index: 7498100 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8147. Min Act: -0.1659
Data Index: 8118593 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8061. Min Act: -0.1498
Data Index: 6075441 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8061. Min Act: -0.1605
Data Index: 1260722 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.8061. Min Act: -0.1652
Data Index: 7196575 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7975. Min Act: -0.1652
Data Index: 7428335 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7889. Min Act: -0.1696
Data Index: 4308771 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7889. Min Act: -0.1531
Data Index: 5573532 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7802. Min Act: -0.1669
Data Index: 1606328 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7802. Min Act: -0.1700
Data Index: 1966132 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7716. Min Act: -0.1675
Data Index: 8341035 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7802. Min Act: -0.1682
Data Index: 8129960 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9767. Min Range: -1.9767
Max Act: 1.7630. Min Act: -0.1697
Data Index: 5684998 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19