Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4503. Min Range: -8.4503
Max Act: 8.4503. Min Act: -0.1700
Data Index: 300444 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.8565. Min Act: -0.1700
Data Index: 8752169 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.8253. Min Act: -0.1700
Data Index: 2899126 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.6690. Min Act: -0.1700
Data Index: 1923108 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.7003. Min Act: -0.1700
Data Index: 8037509 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.7003. Min Act: -0.1700
Data Index: 1704063 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.6065. Min Act: -0.1700
Data Index: 1979604 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.5753. Min Act: -0.1700
Data Index: 7795840 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.5440. Min Act: -0.1700
Data Index: 6216800 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.4815. Min Act: -0.1700
Data Index: 2574899 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.4190. Min Act: -0.1700
Data Index: 3989378 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3878. Min Act: -0.1700
Data Index: 7951027 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.4190. Min Act: -0.1700
Data Index: 6827345 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3878. Min Act: -0.1700
Data Index: 6869263 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3565. Min Act: -0.1700
Data Index: 3770070 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3878. Min Act: -0.1700
Data Index: 2259288 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3878. Min Act: -0.1700
Data Index: 1234994 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3878. Min Act: -0.1700
Data Index: 6586667 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3565. Min Act: -0.1700
Data Index: 1403817 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4503. Min Range: -8.4503
Max Act: 7.3253. Min Act: -0.1700
Data Index: 2699810 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19