Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3439. Min Act: -0.1700
Data Index: 623911 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3439. Min Act: -0.1700
Data Index: 8121762 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3439. Min Act: -0.1700
Data Index: 5281361 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3126. Min Act: -0.1700
Data Index: 4917820 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3439. Min Act: -0.1700
Data Index: 7015758 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3126. Min Act: -0.1700
Data Index: 2982757 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.3126. Min Act: -0.1700
Data Index: 212032 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2501. Min Act: -0.1700
Data Index: 7223281 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2501. Min Act: -0.1700
Data Index: 7902899 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2188. Min Act: -0.1700
Data Index: 8107181 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2188. Min Act: -0.1700
Data Index: 5192033 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2188. Min Act: -0.1700
Data Index: 3580941 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2501. Min Act: -0.1700
Data Index: 5384296 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.1876. Min Act: -0.1700
Data Index: 8121754 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.1563. Min Act: -0.1700
Data Index: 8107184 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.2188. Min Act: -0.1700
Data Index: 3396126 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.1876. Min Act: -0.1700
Data Index: 5030974 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.1563. Min Act: -0.1700
Data Index: 2589321 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.1563. Min Act: -0.1700
Data Index: 241792 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3439. Min Range: -4.3439
Max Act: 4.1876. Min Act: -0.1700
Data Index: 6246060 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19