Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0073. Min Range: -11.0073
Max Act: 11.0073. Min Act: -0.1700
Data Index: 774001 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.9448. Min Act: -0.1700
Data Index: 7049199 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.9448. Min Act: -0.1699
Data Index: 4221173 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.8823. Min Act: -0.1700
Data Index: 8029456 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.8823. Min Act: -0.1700
Data Index: 3971546 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.7573. Min Act: -0.1700
Data Index: 1532537 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6948. Min Act: -0.1700
Data Index: 7216941 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6948. Min Act: -0.1700
Data Index: 1670687 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6948. Min Act: -0.1700
Data Index: 3731204 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6948. Min Act: -0.1700
Data Index: 6328585 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6948. Min Act: -0.1700
Data Index: 8588347 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6323. Min Act: -0.1700
Data Index: 6431446 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6323. Min Act: -0.1700
Data Index: 6300205 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.5698. Min Act: -0.1700
Data Index: 3196605 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6323. Min Act: -0.1700
Data Index: 1855923 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6948. Min Act: -0.1700
Data Index: 3925721 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.6323. Min Act: -0.1700
Data Index: 2092999 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.5698. Min Act: -0.1700
Data Index: 8543448 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.5073. Min Act: -0.1700
Data Index: 8769938 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0073. Min Range: -11.0073
Max Act: 10.5698. Min Act: -0.1700
Data Index: 7335349 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19