Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.5966. Min Act: -0.1700
Data Index: 2204942 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.5654. Min Act: -0.1700
Data Index: 5541495 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.5341. Min Act: -0.1700
Data Index: 328364 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.5029. Min Act: -0.1700
Data Index: 4735058 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.5029. Min Act: -0.1700
Data Index: 3821101 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.4716. Min Act: -0.1700
Data Index: 6821391 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.4716. Min Act: -0.1700
Data Index: 7949253 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.4404. Min Act: -0.1700
Data Index: 3185223 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.4404. Min Act: -0.1700
Data Index: 5329399 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.4404. Min Act: -0.1700
Data Index: 4491948 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3779. Min Act: -0.1700
Data Index: 5272180 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3466. Min Act: -0.1700
Data Index: 8024765 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3779. Min Act: -0.1700
Data Index: 1096770 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3466. Min Act: -0.1700
Data Index: 6621049 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3154. Min Act: -0.1700
Data Index: 2214410 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3466. Min Act: -0.1700
Data Index: 3652993 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3154. Min Act: -0.1700
Data Index: 3089961 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.2841. Min Act: -0.1700
Data Index: 8764682 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.3154. Min Act: -0.1700
Data Index: 898268 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5966. Min Range: -4.5966
Max Act: 4.2841. Min Act: -0.1700
Data Index: 6705765 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19