Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1470 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.8720. Min Act: -0.1700
Data Index: 1165594 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.7783. Min Act: -0.1700
Data Index: 3283345 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.7783. Min Act: -0.1700
Data Index: 461146 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.6845. Min Act: -0.1700
Data Index: 6231855 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.6845. Min Act: -0.1700
Data Index: 5135702 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.6220. Min Act: -0.1700
Data Index: 2030108 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.5283. Min Act: -0.1700
Data Index: 1858706 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.5283. Min Act: -0.1700
Data Index: 916003 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.5283. Min Act: -0.1700
Data Index: 2896989 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4970. Min Act: -0.1700
Data Index: 1677717 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4970. Min Act: -0.1700
Data Index: 4157046 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4658. Min Act: -0.1700
Data Index: 3619409 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4658. Min Act: -0.1700
Data Index: 3046800 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4658. Min Act: -0.1700
Data Index: 7154630 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4658. Min Act: -0.1700
Data Index: 2094941 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4658. Min Act: -0.1700
Data Index: 5935492 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4345. Min Act: -0.1700
Data Index: 6238653 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4658. Min Act: -0.1700
Data Index: 6194818 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4033. Min Act: -0.1700
Data Index: 3209294 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8720. Min Range: -7.8720
Max Act: 7.4033. Min Act: -0.1700
Data Index: 152127 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19