Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.9007. Min Act: -0.1700
Data Index: 3907476 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.7757. Min Act: -0.1700
Data Index: 99163 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.7132. Min Act: -0.1700
Data Index: 8481989 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.5882. Min Act: -0.1700
Data Index: 2283676 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.5882. Min Act: -0.1700
Data Index: 3633405 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.5257. Min Act: -0.1700
Data Index: 6413983 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.5257. Min Act: -0.1700
Data Index: 4587027 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.4632. Min Act: -0.1700
Data Index: 7283931 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.4632. Min Act: -0.1700
Data Index: 7489560 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.3382. Min Act: -0.1700
Data Index: 1510370 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.3382. Min Act: -0.1700
Data Index: 6165460 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2757. Min Act: -0.1700
Data Index: 8011098 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2757. Min Act: -0.1700
Data Index: 6165458 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2757. Min Act: -0.1700
Data Index: 3646415 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2757. Min Act: -0.1700
Data Index: 7142464 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2757. Min Act: -0.1700
Data Index: 3263377 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2757. Min Act: -0.1700
Data Index: 7169117 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2132. Min Act: -0.1700
Data Index: 6311202 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2132. Min Act: -0.1700
Data Index: 3907462 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9007. Min Range: -10.9007
Max Act: 10.2132. Min Act: -0.1700
Data Index: 4576902 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19