Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.6278. Min Act: -0.1686
Data Index: 5642363 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5842. Min Act: -0.1696
Data Index: 5155678 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5929. Min Act: -0.1700
Data Index: 2938669 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5842. Min Act: -0.1696
Data Index: 5338912 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5754. Min Act: -0.1700
Data Index: 5851989 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5754. Min Act: -0.1700
Data Index: 2011013 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5754. Min Act: -0.1700
Data Index: 1625260 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5754. Min Act: -0.1698
Data Index: 7791233 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5667. Min Act: -0.1692
Data Index: 108324 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5667. Min Act: -0.1700
Data Index: 2082693 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5579. Min Act: -0.1700
Data Index: 2457160 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5579. Min Act: -0.1700
Data Index: 7705100 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5579. Min Act: -0.1700
Data Index: 43769 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5579. Min Act: -0.1700
Data Index: 703327 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5579. Min Act: -0.1700
Data Index: 4516238 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5404. Min Act: -0.1698
Data Index: 306274 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5492. Min Act: -0.1700
Data Index: 7136219 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5404. Min Act: -0.1699
Data Index: 6178967 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5492. Min Act: -0.1700
Data Index: 6350079 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6278. Min Range: -1.6278
Max Act: 1.5404. Min Act: -0.1700
Data Index: 7708360 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19