Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2387 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3411. Min Range: -8.3411
Max Act: 8.3411. Min Act: -0.1700
Data Index: 5554878 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3411. Min Range: -8.3411
Max Act: 8.2786. Min Act: -0.1700
Data Index: 5930348 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3411. Min Range: -8.3411
Max Act: 8.0286. Min Act: -0.1700
Data Index: 5884544 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.9661. Min Act: -0.1700
Data Index: 3832047 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.6536. Min Act: -0.1700
Data Index: 2535800 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.6848. Min Act: -0.1700
Data Index: 6618980 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.5911. Min Act: -0.1700
Data Index: 7703589 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.5911. Min Act: -0.1700
Data Index: 7056331 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.5598. Min Act: -0.1700
Data Index: 753414 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.5286. Min Act: -0.1700
Data Index: 1489083 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4661. Min Act: -0.1700
Data Index: 3203934 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4661. Min Act: -0.1700
Data Index: 352639 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4973. Min Act: -0.1700
Data Index: 8255343 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4661. Min Act: -0.1700
Data Index: 5688157 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4348. Min Act: -0.1700
Data Index: 7118593 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4036. Min Act: -0.1700
Data Index: 1380540 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4348. Min Act: -0.1700
Data Index: 7792857 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.3723. Min Act: -0.1700
Data Index: 5507539 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.3723. Min Act: -0.1700
Data Index: 2332688 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3411. Min Range: -8.3411
Max Act: 7.4036. Min Act: -0.1700
Data Index: 1780225 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19