Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 400 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.7866. Min Act: -0.1700
Data Index: 4185592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.7866. Min Act: -0.1700
Data Index: 2971 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7194078 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.7866. Min Act: -0.1700
Data Index: 827477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.7241. Min Act: -0.1700
Data Index: 8200646 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6616. Min Act: -0.1700
Data Index: 8638002 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6303. Min Act: -0.1700
Data Index: 121014 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6616. Min Act: -0.1700
Data Index: 7556977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6303. Min Act: -0.1700
Data Index: 5650107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6303. Min Act: -0.1700
Data Index: 320951 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6616. Min Act: -0.1700
Data Index: 2858842 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7181490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7274004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5991. Min Act: -0.1700
Data Index: 7575474 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5991. Min Act: -0.1700
Data Index: 7072407 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5678. Min Act: -0.1700
Data Index: 6873497 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5678. Min Act: -0.1700
Data Index: 1866125 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5678. Min Act: -0.1700
Data Index: 3537993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5678. Min Act: -0.1700
Data Index: 1353352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7866. Min Range: -4.7866
Max Act: 4.5678. Min Act: -0.1700
Data Index: 4121569 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19