Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.3238. Min Act: -0.1700
Data Index: 4911684 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2924. Min Act: -0.1700
Data Index: 3498344 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.3238. Min Act: -0.1700
Data Index: 605891 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.3238. Min Act: -0.1700
Data Index: 2861257 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2924. Min Act: -0.1700
Data Index: 3972439 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2924. Min Act: -0.1700
Data Index: 8794918 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 5988531 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 6527443 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 6489261 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 5984722 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 61166 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 947098 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 399288 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2610. Min Act: -0.1700
Data Index: 8605373 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2296. Min Act: -0.1700
Data Index: 1437965 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2296. Min Act: -0.1700
Data Index: 6781291 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2296. Min Act: -0.1700
Data Index: 2742576 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1667. Min Act: -0.1700
Data Index: 4692208 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1667. Min Act: -0.1700
Data Index: 8087255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1667. Min Act: -0.1700
Data Index: 8386320 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19