Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4487 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.5057. Min Act: -0.1700
Data Index: 1119401 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.3495. Min Act: -0.1700
Data Index: 6796843 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.2557. Min Act: -0.1700
Data Index: 1119403 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.2557. Min Act: -0.1700
Data Index: 5600529 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.2245. Min Act: -0.1700
Data Index: 1119397 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.1620. Min Act: -0.1700
Data Index: 1119400 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.1932. Min Act: -0.1700
Data Index: 1273062 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.1620. Min Act: -0.1700
Data Index: 1119409 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.0682. Min Act: -0.1700
Data Index: 2544638 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.0370. Min Act: -0.1700
Data Index: 8461807 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.0057. Min Act: -0.1700
Data Index: 1832927 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.0057. Min Act: -0.1700
Data Index: 4282723 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9745. Min Act: -0.1700
Data Index: 7972341 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9745. Min Act: -0.1700
Data Index: 1981980 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9745. Min Act: -0.1700
Data Index: 3219381 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9432. Min Act: -0.1700
Data Index: 4339539 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9432. Min Act: -0.1700
Data Index: 3793051 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9432. Min Act: -0.1700
Data Index: 7233531 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9432. Min Act: -0.1700
Data Index: 5239792 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9120. Min Act: -0.1700
Data Index: 2350493 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19