Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6324. Min Act: -0.1700
Data Index: 291193 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 4267121 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6086. Min Act: -0.1700
Data Index: 2518285 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 3170453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 6299043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 5714782 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 3170209 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 4952503 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 4854292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 105909 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 4652570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 4162171 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 1980597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6086. Min Act: -0.1700
Data Index: 2693129 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 2071652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6086. Min Act: -0.1700
Data Index: 3455236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6086. Min Act: -0.1700
Data Index: 2155057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6086. Min Act: -0.1700
Data Index: 2308618 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 3931560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6324. Min Range: -0.6324
Max Act: 0.6007. Min Act: -0.1700
Data Index: 1823824 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19