Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4902. Min Act: -0.1700
Data Index: 4869779 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.5215. Min Act: -0.1700
Data Index: 6219953 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4902. Min Act: -0.1700
Data Index: 3103529 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4590. Min Act: -0.1700
Data Index: 7643367 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4590. Min Act: -0.1700
Data Index: 3054150 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4902. Min Act: -0.1700
Data Index: 1422911 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4590. Min Act: -0.1700
Data Index: 3425080 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4277. Min Act: -0.1700
Data Index: 4866225 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4277. Min Act: -0.1700
Data Index: 7286276 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4277. Min Act: -0.1700
Data Index: 811134 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4590. Min Act: -0.1700
Data Index: 5067392 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4277. Min Act: -0.1700
Data Index: 3529696 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.4277. Min Act: -0.1700
Data Index: 7073011 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3965. Min Act: -0.1700
Data Index: 8204026 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3965. Min Act: -0.1700
Data Index: 2962158 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3965. Min Act: -0.1700
Data Index: 857700 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3965. Min Act: -0.1700
Data Index: 4691121 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3340. Min Act: -0.1700
Data Index: 4879318 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3340. Min Act: -0.1700
Data Index: 5195087 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5215. Min Range: -5.5215
Max Act: 5.3652. Min Act: -0.1700
Data Index: 4178563 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19