Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5717 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.5959. Min Act: -0.1700
Data Index: 3501422 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.5646. Min Act: -0.1700
Data Index: 7557392 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.3459. Min Act: -0.1700
Data Index: 7472270 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.3459. Min Act: -0.1700
Data Index: 7252035 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.3146. Min Act: -0.1700
Data Index: 7754224 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.3146. Min Act: -0.1700
Data Index: 364136 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.3459. Min Act: -0.1700
Data Index: 7056750 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.2834. Min Act: -0.1700
Data Index: 6299988 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.2521. Min Act: -0.1700
Data Index: 1994594 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.2209. Min Act: -0.1700
Data Index: 2124806 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.2209. Min Act: -0.1700
Data Index: 7181834 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.2209. Min Act: -0.1700
Data Index: 5899534 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.2209. Min Act: -0.1700
Data Index: 488752 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1896. Min Act: -0.1700
Data Index: 8166530 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1584. Min Act: -0.1700
Data Index: 4542846 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1584. Min Act: -0.1700
Data Index: 3849803 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1584. Min Act: -0.1700
Data Index: 7090014 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1584. Min Act: -0.1700
Data Index: 1590545 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1271. Min Act: -0.1700
Data Index: 7405037 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5959. Min Range: -7.5959
Max Act: 7.1271. Min Act: -0.1700
Data Index: 5511961 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19