Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6058 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.7779. Min Act: -0.1700
Data Index: 2225326 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.7779. Min Act: -0.1700
Data Index: 1618385 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.6842. Min Act: -0.1700
Data Index: 2361531 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.7467. Min Act: -0.1700
Data Index: 282171 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.7154. Min Act: -0.1700
Data Index: 530327 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.6217. Min Act: -0.1700
Data Index: 7114672 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.6217. Min Act: -0.1700
Data Index: 8490032 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.6217. Min Act: -0.1700
Data Index: 2690647 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.6217. Min Act: -0.1700
Data Index: 2268459 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5904. Min Act: -0.1700
Data Index: 8540272 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5904. Min Act: -0.1700
Data Index: 7732561 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5592. Min Act: -0.1700
Data Index: 7114671 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5279. Min Act: -0.1700
Data Index: 5616014 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5279. Min Act: -0.1700
Data Index: 4254488 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5279. Min Act: -0.1700
Data Index: 4624619 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5279. Min Act: -0.1700
Data Index: 5966512 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5279. Min Act: -0.1700
Data Index: 3407720 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.4967. Min Act: -0.1700
Data Index: 2505339 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.4967. Min Act: -0.1700
Data Index: 3366990 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7779. Min Range: -5.7779
Max Act: 5.5279. Min Act: -0.1700
Data Index: 7114673 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19