Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4254. Min Range: -9.4254
Max Act: 9.4254. Min Act: -0.1700
Data Index: 3242037 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4254. Min Range: -9.4254
Max Act: 9.1129. Min Act: -0.1700
Data Index: 4708601 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.9879. Min Act: -0.1700
Data Index: 131490 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.9879. Min Act: -0.1700
Data Index: 432649 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.9254. Min Act: -0.1700
Data Index: 5804643 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8629. Min Act: -0.1700
Data Index: 8163221 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8004. Min Act: -0.1700
Data Index: 1005166 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8629. Min Act: -0.1700
Data Index: 6239074 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.9254. Min Act: -0.1700
Data Index: 8579482 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8004. Min Act: -0.1700
Data Index: 3400674 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8004. Min Act: -0.1700
Data Index: 5863086 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8004. Min Act: -0.1700
Data Index: 4321145 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8004. Min Act: -0.1700
Data Index: 6646802 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.7379. Min Act: -0.1700
Data Index: 1557934 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.8004. Min Act: -0.1700
Data Index: 4011493 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.7379. Min Act: -0.1700
Data Index: 6420509 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.7379. Min Act: -0.1700
Data Index: 2453574 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.6754. Min Act: -0.1700
Data Index: 403247 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.6754. Min Act: -0.1700
Data Index: 4312039 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4254. Min Range: -9.4254
Max Act: 8.6754. Min Act: -0.1700
Data Index: 5274151 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19