Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1260. Min Range: -6.1260
Max Act: 6.1260. Min Act: -0.1700
Data Index: 1526310 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.8760. Min Act: -0.1700
Data Index: 8293039 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.8135. Min Act: -0.1700
Data Index: 6441021 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.7510. Min Act: -0.1700
Data Index: 7106984 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.7823. Min Act: -0.1700
Data Index: 6589250 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.7510. Min Act: -0.1700
Data Index: 1447102 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.7198. Min Act: -0.1700
Data Index: 178949 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.7198. Min Act: -0.1700
Data Index: 4248978 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.7198. Min Act: -0.1700
Data Index: 4977235 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.6573. Min Act: -0.1700
Data Index: 938474 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.6885. Min Act: -0.1700
Data Index: 4116655 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.6573. Min Act: -0.1700
Data Index: 1193785 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.6260. Min Act: -0.1700
Data Index: 5678663 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5948. Min Act: -0.1700
Data Index: 6900390 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5635. Min Act: -0.1700
Data Index: 4098138 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 6904751 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4615398 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4388904 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 3456565 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1260. Min Range: -6.1260
Max Act: 5.5323. Min Act: -0.1700
Data Index: 2160587 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19