Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1175. Min Range: -8.1175
Max Act: 8.1175. Min Act: -0.1700
Data Index: 446636 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1175. Min Range: -8.1175
Max Act: 8.1175. Min Act: -0.1700
Data Index: 5292756 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1175. Min Range: -8.1175
Max Act: 8.1175. Min Act: -0.1700
Data Index: 4227998 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.9925. Min Act: -0.1700
Data Index: 5305360 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.9925. Min Act: -0.1700
Data Index: 7266757 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.8675. Min Act: -0.1700
Data Index: 6732798 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.8675. Min Act: -0.1700
Data Index: 5071724 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.8675. Min Act: -0.1700
Data Index: 5564345 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.8050. Min Act: -0.1700
Data Index: 3977505 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.8675. Min Act: -0.1700
Data Index: 283811 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.8050. Min Act: -0.1700
Data Index: 130231 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.7425. Min Act: -0.1700
Data Index: 3296970 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.7425. Min Act: -0.1700
Data Index: 6542972 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.7112. Min Act: -0.1700
Data Index: 7047394 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.6800. Min Act: -0.1700
Data Index: 4026769 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.6800. Min Act: -0.1700
Data Index: 4391365 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.6800. Min Act: -0.1700
Data Index: 6929654 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.6800. Min Act: -0.1700
Data Index: 7318589 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.6800. Min Act: -0.1700
Data Index: 8248343 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1175. Min Range: -8.1175
Max Act: 7.6487. Min Act: -0.1700
Data Index: 8077154 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19