Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8661. Min Act: -0.1700
Data Index: 5056498 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8661. Min Act: -0.1699
Data Index: 7219897 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8661. Min Act: -0.1700
Data Index: 1075531 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 8819975 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 7595431 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8348. Min Act: -0.1700
Data Index: 5039170 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 1277224 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 4478516 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 4852802 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 2628764 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 5290147 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1696
Data Index: 2883768 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 3676159 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.8036. Min Act: -0.1700
Data Index: 8427438 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 13285 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 8078765 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 7013125 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7411. Min Act: -0.1700
Data Index: 1497527 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 3404117 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8661. Min Range: -5.8661
Max Act: 5.7723. Min Act: -0.1700
Data Index: 6781769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19