Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6216 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.5147. Min Act: -0.1700
Data Index: 488190 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4991. Min Act: -0.1700
Data Index: 1139024 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4834. Min Act: -0.1700
Data Index: 8189235 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4678. Min Act: -0.1700
Data Index: 4746366 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4364. Min Act: -0.1700
Data Index: 405465 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4207. Min Act: -0.1700
Data Index: 8808173 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4051. Min Act: -0.1700
Data Index: 6891979 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4207. Min Act: -0.1700
Data Index: 921027 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.4051. Min Act: -0.1700
Data Index: 5220594 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3737. Min Act: -0.1700
Data Index: 8365562 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3737. Min Act: -0.1700
Data Index: 1649641 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3737. Min Act: -0.1700
Data Index: 2909242 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3580. Min Act: -0.1700
Data Index: 1053289 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3266. Min Act: -0.1700
Data Index: 4343535 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3266. Min Act: -0.1700
Data Index: 3624589 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3266. Min Act: -0.1700
Data Index: 2976917 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3266. Min Act: -0.1700
Data Index: 795691 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3266. Min Act: -0.1700
Data Index: 3937154 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.3109. Min Act: -0.1700
Data Index: 4045980 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5147. Min Range: -3.5147
Max Act: 3.2953. Min Act: -0.1700
Data Index: 492397 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19