Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 748 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3796. Min Act: -0.1700
Data Index: 3371837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.4110. Min Act: -0.1700
Data Index: 7959971 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3483. Min Act: -0.1700
Data Index: 3589003 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3796. Min Act: -0.1700
Data Index: 1991171 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3326. Min Act: -0.1700
Data Index: 6666211 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3483. Min Act: -0.1700
Data Index: 6225838 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3169. Min Act: -0.1700
Data Index: 4721898 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3012. Min Act: -0.1700
Data Index: 2901216 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.3169. Min Act: -0.1700
Data Index: 4461111 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2855. Min Act: -0.1700
Data Index: 3784861 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2855. Min Act: -0.1700
Data Index: 4421619 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2855. Min Act: -0.1700
Data Index: 6786307 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2698. Min Act: -0.1700
Data Index: 5017700 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2698. Min Act: -0.1700
Data Index: 2360713 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2541. Min Act: -0.1700
Data Index: 5120022 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2541. Min Act: -0.1700
Data Index: 3577714 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2384. Min Act: -0.1700
Data Index: 1366835 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2384. Min Act: -0.1700
Data Index: 2899215 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2384. Min Act: -0.1700
Data Index: 8619181 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4110. Min Range: -3.4110
Max Act: 3.2226. Min Act: -0.1700
Data Index: 6460468 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19