Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0215. Min Range: -2.0215
Max Act: 2.0215. Min Act: -0.1700
Data Index: 6942509 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.9454. Min Act: -0.1700
Data Index: 4257128 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.9284. Min Act: -0.1700
Data Index: 3632814 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.9114. Min Act: -0.1700
Data Index: 6942507 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8943. Min Act: -0.1700
Data Index: 157774 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8943. Min Act: -0.1699
Data Index: 7881077 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8772. Min Act: -0.1700
Data Index: 3531359 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8772. Min Act: -0.1700
Data Index: 3672784 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8687. Min Act: -0.1700
Data Index: 2615828 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8516. Min Act: -0.1700
Data Index: 1354182 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8516. Min Act: -0.1700
Data Index: 3401567 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8516. Min Act: -0.1700
Data Index: 1890175 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8516. Min Act: -0.1700
Data Index: 7440387 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8430. Min Act: -0.1700
Data Index: 3569119 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8430. Min Act: -0.1700
Data Index: 499034 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8258. Min Act: -0.1700
Data Index: 1269005 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8344. Min Act: -0.1700
Data Index: 7570506 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8173. Min Act: -0.1700
Data Index: 2931930 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8087. Min Act: -0.1700
Data Index: 1609342 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0215. Min Range: -2.0215
Max Act: 1.8173. Min Act: -0.1700
Data Index: 4336979 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19