Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.7229. Min Act: -0.1700
Data Index: 7514639 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.7229. Min Act: -0.1700
Data Index: 3218165 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.7854. Min Act: -0.1700
Data Index: 8093355 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.5979. Min Act: -0.1700
Data Index: 8449318 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.5979. Min Act: -0.1700
Data Index: 6453144 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4729. Min Act: -0.1700
Data Index: 5725961 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4729. Min Act: -0.1700
Data Index: 40691 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4104. Min Act: -0.1700
Data Index: 1819462 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4104. Min Act: -0.1700
Data Index: 4820948 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4104. Min Act: -0.1700
Data Index: 3798555 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4104. Min Act: -0.1700
Data Index: 1863601 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.4104. Min Act: -0.1700
Data Index: 6390437 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3479. Min Act: -0.1700
Data Index: 445961 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3479. Min Act: -0.1700
Data Index: 1899313 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3479. Min Act: -0.1700
Data Index: 2654773 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3167. Min Act: -0.1700
Data Index: 7367728 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3167. Min Act: -0.1700
Data Index: 3411560 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3167. Min Act: -0.1700
Data Index: 5543236 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3167. Min Act: -0.1700
Data Index: 4193578 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7854. Min Range: -7.7854
Max Act: 7.3167. Min Act: -0.1700
Data Index: 3798235 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19