Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0048. Min Range: -9.0048
Max Act: 9.0048. Min Act: -0.1700
Data Index: 8607448 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.5673. Min Act: -0.1700
Data Index: 1103819 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.5048. Min Act: -0.1700
Data Index: 2550894 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.3173. Min Act: -0.1700
Data Index: 2435970 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.3173. Min Act: -0.1700
Data Index: 8285512 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.2548. Min Act: -0.1700
Data Index: 6018692 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.2548. Min Act: -0.1700
Data Index: 1441541 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.2548. Min Act: -0.1700
Data Index: 323398 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.1923. Min Act: -0.1700
Data Index: 2564141 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.1298. Min Act: -0.1700
Data Index: 1793476 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.1298. Min Act: -0.1700
Data Index: 3382019 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.1298. Min Act: -0.1700
Data Index: 1372404 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 2363312 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 5357577 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 948081 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 1902591 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 7563517 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 3110885 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.0673. Min Act: -0.1700
Data Index: 2512365 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0048. Min Range: -9.0048
Max Act: 8.1298. Min Act: -0.1700
Data Index: 5386327 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19