Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6260 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.4656. Min Range: -14.4656
Max Act: 14.4656. Min Act: -0.1700
Data Index: 7364300 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.4656. Min Range: -14.4656
Max Act: 14.0281. Min Act: -0.1700
Data Index: 7076466 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.9031. Min Act: -0.1680
Data Index: 3392337 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.8406. Min Act: -0.1700
Data Index: 5893085 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.8406. Min Act: -0.1700
Data Index: 5848413 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.8406. Min Act: -0.1700
Data Index: 7306224 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.8406. Min Act: -0.1700
Data Index: 8134477 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.7781. Min Act: -0.1700
Data Index: 4924060 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.7781. Min Act: -0.1700
Data Index: 3274982 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.7156. Min Act: -0.1700
Data Index: 2433921 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.6531. Min Act: -0.1700
Data Index: 3645109 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.7156. Min Act: -0.1700
Data Index: 8219326 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.7156. Min Act: -0.1700
Data Index: 8219321 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.7156. Min Act: -0.1691
Data Index: 5163492 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.6531. Min Act: -0.1699
Data Index: 8090725 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.5906. Min Act: -0.1700
Data Index: 2578241 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.6531. Min Act: -0.1700
Data Index: 2648864 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.5906. Min Act: -0.1700
Data Index: 3888297 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.5906. Min Act: -0.1700
Data Index: 7391352 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.4656. Min Range: -14.4656
Max Act: 13.4656. Min Act: -0.1700
Data Index: 3879946 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19