Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2284. Min Range: -6.2284
Max Act: 6.2284. Min Act: -0.1700
Data Index: 6940891 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2284. Min Range: -6.2284
Max Act: 6.1347. Min Act: -0.1700
Data Index: 3189293 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.9159. Min Act: -0.1700
Data Index: 5666403 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.8534. Min Act: -0.1700
Data Index: 3430944 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.8222. Min Act: -0.1700
Data Index: 2200582 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.6347. Min Act: -0.1700
Data Index: 5064235 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.6347. Min Act: -0.1700
Data Index: 4362166 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.6034. Min Act: -0.1700
Data Index: 5976401 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5722. Min Act: -0.1700
Data Index: 4647689 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5097. Min Act: -0.1700
Data Index: 3007812 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5409. Min Act: -0.1700
Data Index: 5571661 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5409. Min Act: -0.1700
Data Index: 8632433 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5097. Min Act: -0.1700
Data Index: 15000 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5409. Min Act: -0.1700
Data Index: 3538035 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.5097. Min Act: -0.1700
Data Index: 6344539 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.4784. Min Act: -0.1700
Data Index: 6262121 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.4472. Min Act: -0.1700
Data Index: 5512826 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.4472. Min Act: -0.1700
Data Index: 2246139 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.4472. Min Act: -0.1700
Data Index: 7200721 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2284. Min Range: -6.2284
Max Act: 5.4472. Min Act: -0.1700
Data Index: 514211 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19