Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5031 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.6252. Min Act: -0.1700
Data Index: 3898910 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.4690. Min Act: -0.1700
Data Index: 4193959 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.2815. Min Act: -0.1700
Data Index: 6033583 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.2190. Min Act: -0.1700
Data Index: 3956728 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.1877. Min Act: -0.1700
Data Index: 2273269 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.1565. Min Act: -0.1700
Data Index: 1294511 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.1252. Min Act: -0.1700
Data Index: 5444777 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.1252. Min Act: -0.1700
Data Index: 1398796 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.1252. Min Act: -0.1700
Data Index: 7548599 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.0940. Min Act: -0.1700
Data Index: 2805110 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6252. Min Range: -6.6252
Max Act: 6.0315. Min Act: -0.1700
Data Index: 7907671 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9377. Min Act: -0.1700
Data Index: 8116415 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9690. Min Act: -0.1700
Data Index: 8578793 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9377. Min Act: -0.1700
Data Index: 6933000 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9065. Min Act: -0.1700
Data Index: 1560434 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9065. Min Act: -0.1700
Data Index: 2748487 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9065. Min Act: -0.1700
Data Index: 7101792 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.8752. Min Act: -0.1700
Data Index: 2532838 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.9065. Min Act: -0.1700
Data Index: 6027148 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6252. Min Range: -6.6252
Max Act: 5.8752. Min Act: -0.1700
Data Index: 4638880 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19