Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8524. Min Range: -10.8524
Max Act: 10.8524. Min Act: -0.1700
Data Index: 7271406 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8524. Min Range: -10.8524
Max Act: 10.7899. Min Act: -0.1700
Data Index: 7271397 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8524. Min Range: -10.8524
Max Act: 10.5399. Min Act: -0.1700
Data Index: 517485 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8524. Min Range: -10.8524
Max Act: 10.2899. Min Act: -0.1700
Data Index: 6579718 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8524. Min Range: -10.8524
Max Act: 10.1649. Min Act: -0.1700
Data Index: 2911360 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.8524. Min Act: -0.1700
Data Index: 3149968 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.7899. Min Act: -0.1700
Data Index: 1966100 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.7274. Min Act: -0.1700
Data Index: 2965180 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.6649. Min Act: -0.1700
Data Index: 8753883 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.6024. Min Act: -0.1700
Data Index: 7271395 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.6024. Min Act: -0.1700
Data Index: 6244624 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.6024. Min Act: -0.1700
Data Index: 5145261 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.6024. Min Act: -0.1700
Data Index: 3829267 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.5399. Min Act: -0.1700
Data Index: 3448929 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.5399. Min Act: -0.1700
Data Index: 5852157 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.4774. Min Act: -0.1700
Data Index: 8123827 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.4774. Min Act: -0.1696
Data Index: 2613580 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.4149. Min Act: -0.1700
Data Index: 1275966 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.4149. Min Act: -0.1700
Data Index: 265802 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8524. Min Range: -10.8524
Max Act: 9.3524. Min Act: -0.1700
Data Index: 3683691 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19