Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.6322. Min Act: -0.1700
Data Index: 2587039 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.3510. Min Act: -0.1700
Data Index: 69035 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.2572. Min Act: -0.1700
Data Index: 1550138 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.2260. Min Act: -0.1700
Data Index: 4108175 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.2572. Min Act: -0.1700
Data Index: 2892910 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.1635. Min Act: -0.1700
Data Index: 539900 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.1322. Min Act: -0.1700
Data Index: 8007593 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.1010. Min Act: -0.1700
Data Index: 2455541 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.1322. Min Act: -0.1700
Data Index: 1196034 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.1010. Min Act: -0.1700
Data Index: 4427995 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.0697. Min Act: -0.1700
Data Index: 4653179 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.0072. Min Act: -0.1700
Data Index: 352620 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6322. Min Range: -7.6322
Max Act: 7.0072. Min Act: -0.1700
Data Index: 4691850 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9760. Min Act: -0.1700
Data Index: 3708141 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9760. Min Act: -0.1700
Data Index: 4981177 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9760. Min Act: -0.1700
Data Index: 6615414 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9447. Min Act: -0.1700
Data Index: 2525718 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9135. Min Act: -0.1700
Data Index: 7142819 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9135. Min Act: -0.1700
Data Index: 3425204 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6322. Min Range: -7.6322
Max Act: 6.9135. Min Act: -0.1700
Data Index: 5953238 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19