Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 7913308 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 1258772 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6994. Min Act: -0.1700
Data Index: 3839370 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6369. Min Act: -0.1700
Data Index: 7289084 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5744. Min Act: -0.1700
Data Index: 3009908 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5744. Min Act: -0.1700
Data Index: 7624596 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5431. Min Act: -0.1700
Data Index: 4105851 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5431. Min Act: -0.1700
Data Index: 708740 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4806. Min Act: -0.1700
Data Index: 7432068 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4494. Min Act: -0.1700
Data Index: 7705989 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4181. Min Act: -0.1700
Data Index: 5248839 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4494. Min Act: -0.1700
Data Index: 3361613 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4494. Min Act: -0.1700
Data Index: 6522295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4494. Min Act: -0.1700
Data Index: 5673535 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4494. Min Act: -0.1700
Data Index: 105473 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4181. Min Act: -0.1700
Data Index: 4404632 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4494. Min Act: -0.1700
Data Index: 5842158 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4181. Min Act: -0.1700
Data Index: 1208596 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4181. Min Act: -0.1700
Data Index: 4917954 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.3869. Min Act: -0.1700
Data Index: 1677185 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19