Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 238 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 3458809 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8654. Min Act: -0.1700
Data Index: 3856647 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8654. Min Act: -0.1700
Data Index: 2317730 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 6554585 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 2839663 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 5855311 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8654. Min Act: -0.1700
Data Index: 4205601 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4254020 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8029. Min Act: -0.1700
Data Index: 2270971 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 413014 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8654. Min Act: -0.1700
Data Index: 3290096 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4728017 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8654. Min Act: -0.1700
Data Index: 7160452 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 2451356 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8029. Min Act: -0.1700
Data Index: 7542529 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8029. Min Act: -0.1700
Data Index: 3259278 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4195397 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.7717. Min Act: -0.1700
Data Index: 7013852 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.8029. Min Act: -0.1700
Data Index: 6801033 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8654. Min Range: -6.8654
Max Act: 6.7717. Min Act: -0.1700
Data Index: 3531483 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19