Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3100. Min Range: -7.3100
Max Act: 7.3100. Min Act: -0.1700
Data Index: 5428740 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3100. Min Range: -7.3100
Max Act: 7.2788. Min Act: -0.1700
Data Index: 8769714 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3100. Min Range: -7.3100
Max Act: 7.1538. Min Act: -0.1700
Data Index: 3268718 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3100. Min Range: -7.3100
Max Act: 7.0913. Min Act: -0.1700
Data Index: 3454292 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9975. Min Act: -0.1700
Data Index: 1877878 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9975. Min Act: -0.1700
Data Index: 2331421 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9975. Min Act: -0.1700
Data Index: 915404 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9975. Min Act: -0.1700
Data Index: 5244914 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9663. Min Act: -0.1700
Data Index: 7647150 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9663. Min Act: -0.1700
Data Index: 1349240 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9350. Min Act: -0.1700
Data Index: 2970364 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9350. Min Act: -0.1700
Data Index: 5790015 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9038. Min Act: -0.1700
Data Index: 1504842 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9350. Min Act: -0.1700
Data Index: 1318562 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9038. Min Act: -0.1700
Data Index: 285645 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9038. Min Act: -0.1700
Data Index: 3007649 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9038. Min Act: -0.1700
Data Index: 7536575 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.9038. Min Act: -0.1700
Data Index: 2735509 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.8413. Min Act: -0.1700
Data Index: 1271227 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3100. Min Range: -7.3100
Max Act: 6.8413. Min Act: -0.1700
Data Index: 2994187 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19