Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.9977. Min Act: -0.1700
Data Index: 483119 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.8233. Min Act: -0.1700
Data Index: 4975486 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.8074. Min Act: -0.1700
Data Index: 2028326 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7914. Min Act: -0.1700
Data Index: 7819423 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7596. Min Act: -0.1700
Data Index: 4925557 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7596. Min Act: -0.1700
Data Index: 4217323 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7276. Min Act: -0.1700
Data Index: 1904559 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7276. Min Act: -0.1700
Data Index: 6485157 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7436. Min Act: -0.1700
Data Index: 2409773 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7596. Min Act: -0.1700
Data Index: 7204595 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7436. Min Act: -0.1700
Data Index: 8390757 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7276. Min Act: -0.1700
Data Index: 1597224 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6956. Min Act: -0.1700
Data Index: 5694172 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6796. Min Act: -0.1700
Data Index: 2709660 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6796. Min Act: -0.1700
Data Index: 656592 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.7116. Min Act: -0.1700
Data Index: 3365364 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6476. Min Act: -0.1700
Data Index: 8417942 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6315. Min Act: -0.1700
Data Index: 8385085 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6315. Min Act: -0.1700
Data Index: 1832463 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9977. Min Range: -2.9977
Max Act: 2.6476. Min Act: -0.1700
Data Index: 3777827 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19