Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.5530. Min Act: -0.1700
Data Index: 8574672 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.5218. Min Act: -0.1700
Data Index: 377423 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.4905. Min Act: -0.1700
Data Index: 4759965 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.4905. Min Act: -0.1700
Data Index: 3425936 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.4593. Min Act: -0.1700
Data Index: 7257425 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.4280. Min Act: -0.1700
Data Index: 2728309 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.4280. Min Act: -0.1700
Data Index: 5686136 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3968. Min Act: -0.1700
Data Index: 4951179 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.4280. Min Act: -0.1700
Data Index: 4759967 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3968. Min Act: -0.1700
Data Index: 6297366 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3968. Min Act: -0.1700
Data Index: 7220318 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3655. Min Act: -0.1700
Data Index: 7239075 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3655. Min Act: -0.1700
Data Index: 1490656 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 1882281 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 3260051 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 7418861 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 7418860 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 3748138 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 2579981 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5530. Min Range: -5.5530
Max Act: 5.3343. Min Act: -0.1700
Data Index: 5658904 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19