Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.5340. Min Act: -0.1700
Data Index: 1009160 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.5340. Min Act: -0.1700
Data Index: 4163974 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.5340. Min Act: -0.1700
Data Index: 7395552 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.4090. Min Act: -0.1700
Data Index: 6476626 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.3153. Min Act: -0.1700
Data Index: 790917 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2840. Min Act: -0.1700
Data Index: 6061167 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2840. Min Act: -0.1700
Data Index: 1044162 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2528. Min Act: -0.1700
Data Index: 5813876 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2528. Min Act: -0.1700
Data Index: 1735390 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2528. Min Act: -0.1700
Data Index: 2374059 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2840. Min Act: -0.1700
Data Index: 7395551 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2528. Min Act: -0.1700
Data Index: 8463179 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2528. Min Act: -0.1700
Data Index: 3794493 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2215. Min Act: -0.1700
Data Index: 2320781 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2215. Min Act: -0.1700
Data Index: 4729860 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.1903. Min Act: -0.1700
Data Index: 2090766 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2215. Min Act: -0.1700
Data Index: 7598521 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2215. Min Act: -0.1700
Data Index: 8425086 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2215. Min Act: -0.1700
Data Index: 1280988 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5340. Min Range: -6.5340
Max Act: 6.2215. Min Act: -0.1700
Data Index: 3652946 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19