Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6352. Min Range: -6.6352
Max Act: 6.6352. Min Act: -0.1700
Data Index: 845831 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6352. Min Range: -6.6352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 492908 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6352. Min Range: -6.6352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 2644819 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6352. Min Range: -6.6352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 7241200 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.9790. Min Act: -0.1700
Data Index: 5555919 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 4693668 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.9165. Min Act: -0.1700
Data Index: 343035 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 3145563 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 1295069 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 5704232 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 2277763 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8540. Min Act: -0.1700
Data Index: 7164687 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.7915. Min Act: -0.1700
Data Index: 3877020 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1078483 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1006517 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1578871 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6337236 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6622675 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 8735663 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6352. Min Range: -6.6352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5667053 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19