Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 893190 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7646. Min Act: -0.1700
Data Index: 1428688 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7021. Min Act: -0.1700
Data Index: 2400084 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7021. Min Act: -0.1700
Data Index: 1856881 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6709. Min Act: -0.1700
Data Index: 8368524 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6709. Min Act: -0.1700
Data Index: 3976424 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6396. Min Act: -0.1700
Data Index: 8314545 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6084. Min Act: -0.1700
Data Index: 2353677 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 4597492 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6396. Min Act: -0.1700
Data Index: 6923409 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 3350168 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 3843778 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 2397633 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 2739124 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 1536894 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5771. Min Act: -0.1700
Data Index: 2276441 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5459. Min Act: -0.1700
Data Index: 202424 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5459. Min Act: -0.1700
Data Index: 169725 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5459. Min Act: -0.1700
Data Index: 7779455 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5146. Min Act: -0.1700
Data Index: 7746763 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19