Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3183 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.7813. Min Act: -0.1700
Data Index: 8756810 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.7494. Min Act: -0.1700
Data Index: 846953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.7174. Min Act: -0.1700
Data Index: 1950491 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.7334. Min Act: -0.1700
Data Index: 3305985 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6854. Min Act: -0.1700
Data Index: 8425737 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.7014. Min Act: -0.1700
Data Index: 3226478 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6854. Min Act: -0.1700
Data Index: 7284503 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6694. Min Act: -0.1700
Data Index: 2658171 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6373. Min Act: -0.1700
Data Index: 3438650 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6213. Min Act: -0.1700
Data Index: 2233608 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6052. Min Act: -0.1700
Data Index: 6611720 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6052. Min Act: -0.1700
Data Index: 5056131 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.5730. Min Act: -0.1700
Data Index: 3684452 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6052. Min Act: -0.1700
Data Index: 4848212 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.5891. Min Act: -0.1700
Data Index: 8086615 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6052. Min Act: -0.1700
Data Index: 4670841 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.6213. Min Act: -0.1700
Data Index: 1794610 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.5891. Min Act: -0.1700
Data Index: 5063780 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.5891. Min Act: -0.1700
Data Index: 8291851 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7813. Min Range: -2.7813
Max Act: 2.5891. Min Act: -0.1700
Data Index: 447070 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19