Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2122 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9380. Min Act: -0.1700
Data Index: 8736253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9380. Min Act: -0.1700
Data Index: 5316138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9380. Min Act: -0.1700
Data Index: 7355121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9380. Min Act: -0.1700
Data Index: 631126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7818. Min Act: -0.1700
Data Index: 5538407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7818. Min Act: -0.1700
Data Index: 6283953 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6880. Min Act: -0.1700
Data Index: 7543104 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6255. Min Act: -0.1700
Data Index: 7828539 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5943. Min Act: -0.1700
Data Index: 3383501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6255. Min Act: -0.1700
Data Index: 4522950 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5630. Min Act: -0.1700
Data Index: 7197387 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5630. Min Act: -0.1700
Data Index: 2971796 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5318. Min Act: -0.1700
Data Index: 7579459 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5318. Min Act: -0.1700
Data Index: 6818301 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5318. Min Act: -0.1700
Data Index: 1072286 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5005. Min Act: -0.1700
Data Index: 6876420 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5318. Min Act: -0.1700
Data Index: 6451871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.4693. Min Act: -0.1700
Data Index: 4698819 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5005. Min Act: -0.1700
Data Index: 5655627 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5005. Min Act: -0.1700
Data Index: 2629575 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19