Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5821 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4272. Min Range: -8.4272
Max Act: 8.4272. Min Act: -0.1700
Data Index: 6809979 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4272. Min Range: -8.4272
Max Act: 8.3022. Min Act: -0.1700
Data Index: 6433858 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4272. Min Range: -8.4272
Max Act: 8.1147. Min Act: -0.1700
Data Index: 7014968 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4272. Min Range: -8.4272
Max Act: 8.0522. Min Act: -0.1700
Data Index: 2499452 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4272. Min Range: -8.4272
Max Act: 8.0834. Min Act: -0.1700
Data Index: 6420468 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.8959. Min Act: -0.1700
Data Index: 3526258 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.8647. Min Act: -0.1700
Data Index: 7874201 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.8647. Min Act: -0.1700
Data Index: 6257096 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.8959. Min Act: -0.1700
Data Index: 8327611 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.8334. Min Act: -0.1700
Data Index: 5484540 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.8022. Min Act: -0.1700
Data Index: 5919555 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.7397. Min Act: -0.1700
Data Index: 6011845 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.7397. Min Act: -0.1700
Data Index: 6290678 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.6772. Min Act: -0.1700
Data Index: 4869907 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.7084. Min Act: -0.1700
Data Index: 5401624 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.6459. Min Act: -0.1700
Data Index: 1733357 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.6147. Min Act: -0.1700
Data Index: 1202505 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.6147. Min Act: -0.1700
Data Index: 5557049 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.6147. Min Act: -0.1700
Data Index: 3627958 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4272. Min Range: -8.4272
Max Act: 7.5834. Min Act: -0.1700
Data Index: 792408 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19