Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.5760. Min Act: -0.1700
Data Index: 5318771 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.4822. Min Act: -0.1700
Data Index: 8181494 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.4822. Min Act: -0.1700
Data Index: 3020918 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.4822. Min Act: -0.1700
Data Index: 1725738 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.4197. Min Act: -0.1700
Data Index: 8480882 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.4197. Min Act: -0.1700
Data Index: 5357929 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.3885. Min Act: -0.1700
Data Index: 5646243 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.3572. Min Act: -0.1700
Data Index: 6168632 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.4197. Min Act: -0.1700
Data Index: 4457311 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2635. Min Act: -0.1700
Data Index: 2349810 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2947. Min Act: -0.1700
Data Index: 5485631 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2635. Min Act: -0.1700
Data Index: 1617873 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2322. Min Act: -0.1700
Data Index: 3852121 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2322. Min Act: -0.1700
Data Index: 4108451 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2322. Min Act: -0.1700
Data Index: 2013504 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2010. Min Act: -0.1700
Data Index: 3270377 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.2010. Min Act: -0.1700
Data Index: 2475280 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.1697. Min Act: -0.1700
Data Index: 3020917 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4911611 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5760. Min Range: -4.5760
Max Act: 4.1385. Min Act: -0.1700
Data Index: 3459754 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19