Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2037. Min Range: -5.2037
Max Act: 5.2037. Min Act: -0.1700
Data Index: 6454623 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.7349. Min Act: -0.1700
Data Index: 8385908 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.6724. Min Act: -0.1700
Data Index: 375137 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.6412. Min Act: -0.1700
Data Index: 2574314 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.6412. Min Act: -0.1700
Data Index: 5506358 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.6099. Min Act: -0.1700
Data Index: 362321 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.5787. Min Act: -0.1700
Data Index: 4799805 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1033112 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.5474. Min Act: -0.1700
Data Index: 6856586 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.5162. Min Act: -0.1700
Data Index: 434203 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.5162. Min Act: -0.1700
Data Index: 527668 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4849. Min Act: -0.1700
Data Index: 337946 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4849. Min Act: -0.1700
Data Index: 7486642 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4849. Min Act: -0.1700
Data Index: 8661885 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4849. Min Act: -0.1700
Data Index: 5618063 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4849. Min Act: -0.1700
Data Index: 3765419 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4537. Min Act: -0.1700
Data Index: 5985330 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4537. Min Act: -0.1700
Data Index: 8354608 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4224. Min Act: -0.1700
Data Index: 4763377 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2037. Min Range: -5.2037
Max Act: 4.4224. Min Act: -0.1700
Data Index: 254268 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19