Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.9405. Min Act: -0.1700
Data Index: 535797 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.9093. Min Act: -0.1700
Data Index: 4101563 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.8468. Min Act: -0.1700
Data Index: 1748204 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.8155. Min Act: -0.1700
Data Index: 4346365 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.8155. Min Act: -0.1700
Data Index: 198398 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.7843. Min Act: -0.1700
Data Index: 8471982 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.7843. Min Act: -0.1700
Data Index: 7624069 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.7530. Min Act: -0.1700
Data Index: 1221596 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.6905. Min Act: -0.1700
Data Index: 4778624 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.7218. Min Act: -0.1700
Data Index: 1539427 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.6593. Min Act: -0.1700
Data Index: 4968976 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.6280. Min Act: -0.1700
Data Index: 1778928 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.6280. Min Act: -0.1700
Data Index: 3551841 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.5968. Min Act: -0.1700
Data Index: 8825558 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.6280. Min Act: -0.1700
Data Index: 4995212 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.5968. Min Act: -0.1700
Data Index: 2554113 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.5655. Min Act: -0.1700
Data Index: 5905456 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.5655. Min Act: -0.1700
Data Index: 889114 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.5655. Min Act: -0.1700
Data Index: 4352902 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9405. Min Range: -5.9405
Max Act: 5.5030. Min Act: -0.1700
Data Index: 1850879 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19