Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.4487. Min Act: -0.1700
Data Index: 114701 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.3672. Min Act: -0.1700
Data Index: 4284714 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.3672. Min Act: -0.1700
Data Index: 2190554 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.3180. Min Act: -0.1700
Data Index: 6170706 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.3016. Min Act: -0.1700
Data Index: 2263994 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2686. Min Act: -0.1700
Data Index: 5729210 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2686. Min Act: -0.1700
Data Index: 3788027 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2356. Min Act: -0.1700
Data Index: 5502427 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2356. Min Act: -0.1700
Data Index: 4809551 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2356. Min Act: -0.1700
Data Index: 4179724 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2356. Min Act: -0.1700
Data Index: 2680705 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2356. Min Act: -0.1700
Data Index: 3159998 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2190. Min Act: -0.1700
Data Index: 3864223 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2190. Min Act: -0.1700
Data Index: 8787985 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2356. Min Act: -0.1700
Data Index: 2674493 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2024. Min Act: -0.1700
Data Index: 4558969 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2024. Min Act: -0.1700
Data Index: 4411479 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.1858. Min Act: -0.1700
Data Index: 3851649 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2024. Min Act: -0.1700
Data Index: 4428683 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4487. Min Range: -2.4487
Max Act: 2.2024. Min Act: -0.1700
Data Index: 5839150 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19