Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5998 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2395. Min Range: -5.2395
Max Act: 5.2395. Min Act: -0.1700
Data Index: 7653417 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2395. Min Range: -5.2395
Max Act: 5.1145. Min Act: -0.1700
Data Index: 5325996 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2395. Min Range: -5.2395
Max Act: 5.0833. Min Act: -0.1700
Data Index: 656114 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2395. Min Range: -5.2395
Max Act: 5.0520. Min Act: -0.1700
Data Index: 2377823 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2395. Min Range: -5.2395
Max Act: 5.0520. Min Act: -0.1700
Data Index: 1639315 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2395. Min Range: -5.2395
Max Act: 5.0208. Min Act: -0.1700
Data Index: 3048514 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.9895. Min Act: -0.1700
Data Index: 71643 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.9895. Min Act: -0.1700
Data Index: 6798739 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.9895. Min Act: -0.1699
Data Index: 2421698 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.9583. Min Act: -0.1700
Data Index: 8047469 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.9270. Min Act: -0.1700
Data Index: 7855843 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.9270. Min Act: -0.1700
Data Index: 4263782 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1700
Data Index: 1926678 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8645. Min Act: -0.1700
Data Index: 2903140 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1700
Data Index: 7169376 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5325995 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1700
Data Index: 1458509 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5368531 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5603034 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2395. Min Range: -5.2395
Max Act: 4.8958. Min Act: -0.1698
Data Index: 950331 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19