Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4162 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 522562 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.5415. Min Act: -0.1700
Data Index: 1936298 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4790. Min Act: -0.1700
Data Index: 5065371 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4477. Min Act: -0.1700
Data Index: 5065370 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4165. Min Act: -0.1700
Data Index: 88515 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3852. Min Act: -0.1700
Data Index: 743703 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3852. Min Act: -0.1700
Data Index: 1598987 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3852. Min Act: -0.1700
Data Index: 7509089 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3227. Min Act: -0.1700
Data Index: 334892 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3227. Min Act: -0.1700
Data Index: 6819078 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2915. Min Act: -0.1700
Data Index: 7930990 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2915. Min Act: -0.1700
Data Index: 6819071 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2915. Min Act: -0.1700
Data Index: 1731733 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2602. Min Act: -0.1700
Data Index: 5749219 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2290. Min Act: -0.1700
Data Index: 1900197 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2602. Min Act: -0.1700
Data Index: 6190537 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2290. Min Act: -0.1700
Data Index: 722747 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.1665. Min Act: -0.1700
Data Index: 6819076 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.1665. Min Act: -0.1700
Data Index: 7221724 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.1665. Min Act: -0.1700
Data Index: 1168526 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19