Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1666. Min Range: -6.1666
Max Act: 6.1666. Min Act: -0.1700
Data Index: 2191553 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1666. Min Range: -6.1666
Max Act: 6.1666. Min Act: -0.1700
Data Index: 8365757 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1666. Min Range: -6.1666
Max Act: 6.1354. Min Act: -0.1700
Data Index: 8799047 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1666. Min Range: -6.1666
Max Act: 6.0416. Min Act: -0.1700
Data Index: 8345314 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1666. Min Range: -6.1666
Max Act: 6.0104. Min Act: -0.1700
Data Index: 2083409 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.9479. Min Act: -0.1700
Data Index: 5795326 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.8854. Min Act: -0.1700
Data Index: 422963 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.8229. Min Act: -0.1700
Data Index: 4024386 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.8229. Min Act: -0.1700
Data Index: 2400697 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.7916. Min Act: -0.1700
Data Index: 2811819 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.7604. Min Act: -0.1700
Data Index: 4785496 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.7291. Min Act: -0.1700
Data Index: 7338784 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.6979. Min Act: -0.1700
Data Index: 8275808 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.7291. Min Act: -0.1700
Data Index: 5645727 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.7291. Min Act: -0.1700
Data Index: 1439358 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.6979. Min Act: -0.1700
Data Index: 7745336 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.7291. Min Act: -0.1700
Data Index: 4661776 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.6354. Min Act: -0.1700
Data Index: 215505 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.6666. Min Act: -0.1700
Data Index: 4325272 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1666. Min Range: -6.1666
Max Act: 5.6666. Min Act: -0.1700
Data Index: 4551573 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19