Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 243 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.7315. Min Act: -0.1700
Data Index: 414217 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.6690. Min Act: -0.1700
Data Index: 6829410 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.4502. Min Act: -0.1700
Data Index: 5699252 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.4190. Min Act: -0.1700
Data Index: 4073632 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.4190. Min Act: -0.1700
Data Index: 4549800 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.3877. Min Act: -0.1700
Data Index: 4208271 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.3565. Min Act: -0.1700
Data Index: 2783106 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.3565. Min Act: -0.1700
Data Index: 6291077 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.3252. Min Act: -0.1700
Data Index: 3675895 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.3252. Min Act: -0.1700
Data Index: 4321540 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.2940. Min Act: -0.1700
Data Index: 804168 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.2627. Min Act: -0.1700
Data Index: 4835002 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.2315. Min Act: -0.1700
Data Index: 357277 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.2002. Min Act: -0.1700
Data Index: 2981876 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.1690. Min Act: -0.1700
Data Index: 186093 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.1377. Min Act: -0.1700
Data Index: 2479434 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.1690. Min Act: -0.1700
Data Index: 6789613 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.2002. Min Act: -0.1700
Data Index: 1915645 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.1690. Min Act: -0.1700
Data Index: 4659743 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7315. Min Range: -6.7315
Max Act: 6.1690. Min Act: -0.1700
Data Index: 7619150 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19