Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0932. Min Range: -5.0932
Max Act: 5.0932. Min Act: -0.1700
Data Index: 6312464 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9995. Min Act: -0.1700
Data Index: 7316271 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9682. Min Act: -0.1700
Data Index: 270201 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9682. Min Act: -0.1700
Data Index: 1414534 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8745. Min Act: -0.1700
Data Index: 754504 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9057. Min Act: -0.1700
Data Index: 3478238 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8745. Min Act: -0.1700
Data Index: 6822551 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8120. Min Act: -0.1700
Data Index: 7215871 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8120. Min Act: -0.1700
Data Index: 8744683 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7807. Min Act: -0.1700
Data Index: 1739854 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7807. Min Act: -0.1700
Data Index: 1121804 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7495. Min Act: -0.1700
Data Index: 189795 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7495. Min Act: -0.1700
Data Index: 5047738 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7495. Min Act: -0.1700
Data Index: 2390925 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7495. Min Act: -0.1700
Data Index: 3782646 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7182. Min Act: -0.1700
Data Index: 3876100 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7182. Min Act: -0.1700
Data Index: 656678 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7182. Min Act: -0.1700
Data Index: 3563050 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7182. Min Act: -0.1700
Data Index: 7210844 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.7182. Min Act: -0.1700
Data Index: 5830766 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19