Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 566 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.9285. Min Act: -0.1699
Data Index: 6138586 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.8348. Min Act: -0.1700
Data Index: 5368453 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.8660. Min Act: -0.1700
Data Index: 974626 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1483547 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.7723. Min Act: -0.1700
Data Index: 6752494 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.8035. Min Act: -0.1700
Data Index: 4434750 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.8035. Min Act: -0.1700
Data Index: 5764751 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.7723. Min Act: -0.1700
Data Index: 4752662 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.6785. Min Act: -0.1700
Data Index: 5914034 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.6785. Min Act: -0.1700
Data Index: 6746214 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.6785. Min Act: -0.1700
Data Index: 5516341 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.6785. Min Act: -0.1694
Data Index: 6672457 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.6473. Min Act: -0.1700
Data Index: 1205206 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.6785. Min Act: -0.1698
Data Index: 7840642 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.5223. Min Act: -0.1700
Data Index: 943118 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.5535. Min Act: -0.1700
Data Index: 6759609 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.5535. Min Act: -0.1700
Data Index: 3032948 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.5535. Min Act: -0.1700
Data Index: 3321436 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.5535. Min Act: -0.1700
Data Index: 7738803 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9285. Min Range: -5.9285
Max Act: 5.5535. Min Act: -0.1700
Data Index: 2807076 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19