Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 318 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.4379. Min Act: -0.1700
Data Index: 7003665 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.4066. Min Act: -0.1700
Data Index: 6833192 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.3754. Min Act: -0.1700
Data Index: 3333723 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2504. Min Act: -0.1700
Data Index: 7918477 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2191. Min Act: -0.1700
Data Index: 8636961 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2191. Min Act: -0.1700
Data Index: 1375578 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.2191. Min Act: -0.1700
Data Index: 5426955 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.1566. Min Act: -0.1700
Data Index: 1981997 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.1566. Min Act: -0.1700
Data Index: 7060621 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.1566. Min Act: -0.1700
Data Index: 1375580 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.1566. Min Act: -0.1700
Data Index: 8220250 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0941. Min Act: -0.1700
Data Index: 4315841 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0941. Min Act: -0.1699
Data Index: 1704485 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0316. Min Act: -0.1700
Data Index: 7441809 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0316. Min Act: -0.1700
Data Index: 50764 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0316. Min Act: -0.1700
Data Index: 820035 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0316. Min Act: -0.1700
Data Index: 8198517 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0004. Min Act: -0.1700
Data Index: 6788684 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0316. Min Act: -0.1700
Data Index: 3084463 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4379. Min Range: -6.4379
Max Act: 6.0629. Min Act: -0.1700
Data Index: 5642482 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19