Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.7310. Min Act: -0.1700
Data Index: 4252344 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.7154. Min Act: -0.1700
Data Index: 4294515 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6841. Min Act: -0.1700
Data Index: 2414437 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6841. Min Act: -0.1700
Data Index: 4804407 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6528. Min Act: -0.1700
Data Index: 8642130 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6372. Min Act: -0.1700
Data Index: 58427 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6059. Min Act: -0.1700
Data Index: 2537620 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6372. Min Act: -0.1700
Data Index: 8235770 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6215. Min Act: -0.1700
Data Index: 5374646 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6059. Min Act: -0.1700
Data Index: 1981772 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6059. Min Act: -0.1700
Data Index: 3273679 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5902. Min Act: -0.1700
Data Index: 7471628 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.6059. Min Act: -0.1700
Data Index: 1854572 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5902. Min Act: -0.1700
Data Index: 7377128 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5902. Min Act: -0.1700
Data Index: 6775677 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5276. Min Act: -0.1700
Data Index: 6731836 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5276. Min Act: -0.1700
Data Index: 8198889 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5276. Min Act: -0.1700
Data Index: 5754586 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5276. Min Act: -0.1700
Data Index: 1360619 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7310. Min Range: -3.7310
Max Act: 3.5276. Min Act: -0.1700
Data Index: 7131127 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19