Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0534. Min Range: -7.0534
Max Act: 7.0534. Min Act: -0.1700
Data Index: 5995834 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0534. Min Range: -7.0534
Max Act: 7.0534. Min Act: -0.1700
Data Index: 1828406 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.9597. Min Act: -0.1700
Data Index: 5856203 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.9597. Min Act: -0.1700
Data Index: 8559190 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.8034. Min Act: -0.1700
Data Index: 1847272 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.8034. Min Act: -0.1700
Data Index: 1832160 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.7409. Min Act: -0.1700
Data Index: 6438712 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6784. Min Act: -0.1700
Data Index: 2381884 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 1854075 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 5613144 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 7031368 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 6651303 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 1185625 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 3095425 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 5497255 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.5847. Min Act: -0.1700
Data Index: 2744322 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.5847. Min Act: -0.1700
Data Index: 6426863 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.5534. Min Act: -0.1700
Data Index: 3571626 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.6159. Min Act: -0.1700
Data Index: 2865603 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0534. Min Range: -7.0534
Max Act: 6.5534. Min Act: -0.1700
Data Index: 4961100 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19