Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4514 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4814. Min Range: -12.4814
Max Act: 12.4814. Min Act: -0.1700
Data Index: 8737226 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4814. Min Range: -12.4814
Max Act: 12.2314. Min Act: -0.1700
Data Index: 2993566 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4814. Min Range: -12.4814
Max Act: 12.0439. Min Act: -0.1700
Data Index: 3534456 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4814. Min Range: -12.4814
Max Act: 12.0439. Min Act: -0.1700
Data Index: 5255227 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.9814. Min Act: -0.1700
Data Index: 4606034 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.9814. Min Act: -0.1700
Data Index: 2161464 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.9814. Min Act: -0.1700
Data Index: 5130521 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.8564. Min Act: -0.1700
Data Index: 3048735 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.7939. Min Act: -0.1700
Data Index: 7025711 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.7314. Min Act: -0.1700
Data Index: 6219698 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.7314. Min Act: -0.1700
Data Index: 2488512 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.7314. Min Act: -0.1700
Data Index: 7623720 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.6689. Min Act: -0.1700
Data Index: 780165 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.6689. Min Act: -0.1700
Data Index: 2201135 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.6064. Min Act: -0.1700
Data Index: 3919003 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.5439. Min Act: -0.1700
Data Index: 5296924 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.6064. Min Act: -0.1700
Data Index: 5571888 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.5439. Min Act: -0.1700
Data Index: 3534453 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.5439. Min Act: -0.1700
Data Index: 624057 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4814. Min Range: -12.4814
Max Act: 11.4814. Min Act: -0.1700
Data Index: 5984143 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19