Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2414 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.8926. Min Act: -0.1700
Data Index: 5052300 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.8301. Min Act: -0.1700
Data Index: 5385056 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.7676. Min Act: -0.1700
Data Index: 2820490 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.7364. Min Act: -0.1700
Data Index: 2730380 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.7364. Min Act: -0.1700
Data Index: 4877785 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.7051. Min Act: -0.1700
Data Index: 7311638 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.6739. Min Act: -0.1700
Data Index: 699031 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.6426. Min Act: -0.1700
Data Index: 3343918 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.6114. Min Act: -0.1700
Data Index: 3921008 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.6114. Min Act: -0.1700
Data Index: 325880 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5801. Min Act: -0.1700
Data Index: 386230 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5489. Min Act: -0.1700
Data Index: 7506475 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5489. Min Act: -0.1700
Data Index: 3989410 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5176. Min Act: -0.1700
Data Index: 7190445 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5176. Min Act: -0.1700
Data Index: 4116203 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.4864. Min Act: -0.1700
Data Index: 1213938 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5489. Min Act: -0.1700
Data Index: 1063021 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.5176. Min Act: -0.1700
Data Index: 6874014 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.4551. Min Act: -0.1700
Data Index: 2485254 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8926. Min Range: -6.8926
Max Act: 6.4239. Min Act: -0.1700
Data Index: 5698658 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19