Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6235 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8885. Min Act: -0.1700
Data Index: 7904932 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8572. Min Act: -0.1700
Data Index: 6771477 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8572. Min Act: -0.1700
Data Index: 3675548 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8260. Min Act: -0.1700
Data Index: 1722641 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8260. Min Act: -0.1700
Data Index: 8627477 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.8260. Min Act: -0.1700
Data Index: 6652604 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7635. Min Act: -0.1700
Data Index: 3543895 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7635. Min Act: -0.1700
Data Index: 814197 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7635. Min Act: -0.1700
Data Index: 361599 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7322. Min Act: -0.1700
Data Index: 1617891 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7322. Min Act: -0.1700
Data Index: 8627478 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7322. Min Act: -0.1700
Data Index: 4858042 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2811164 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7635. Min Act: -0.1700
Data Index: 7904930 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7322. Min Act: -0.1700
Data Index: 1155287 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 296298 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 8556548 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2195826 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 3794301 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8885. Min Range: -5.8885
Max Act: 5.7010. Min Act: -0.1700
Data Index: 1916747 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19