Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 459 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.5463. Min Act: -0.1700
Data Index: 3563578 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.2963. Min Act: -0.1700
Data Index: 4984159 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.2338. Min Act: -0.1700
Data Index: 6990716 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.2338. Min Act: -0.1700
Data Index: 3182872 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.2025. Min Act: -0.1700
Data Index: 1605407 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7830248 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7917621 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2514946 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.1087. Min Act: -0.1700
Data Index: 8394312 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0775. Min Act: -0.1700
Data Index: 7522214 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0775. Min Act: -0.1700
Data Index: 3087687 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0462. Min Act: -0.1700
Data Index: 365712 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0462. Min Act: -0.1700
Data Index: 4016143 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0462. Min Act: -0.1700
Data Index: 256573 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0462. Min Act: -0.1700
Data Index: 5313706 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0150. Min Act: -0.1700
Data Index: 8565402 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0150. Min Act: -0.1700
Data Index: 8703007 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0150. Min Act: -0.1700
Data Index: 756520 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5463. Min Range: -4.5463
Max Act: 4.0150. Min Act: -0.1700
Data Index: 7571762 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5463. Min Range: -4.5463
Max Act: 3.9837. Min Act: -0.1700
Data Index: 5561388 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19