Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1738. Min Act: -0.1700
Data Index: 1679362 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1265. Min Act: -0.1700
Data Index: 6993052 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.1108. Min Act: -0.1700
Data Index: 7702300 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 923021 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 7197185 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 8725885 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 3550602 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 5005985 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0950. Min Act: -0.1700
Data Index: 2105432 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 7021366 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 6757201 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 1682827 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 6728434 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 6409442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 5589936 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 12662 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 5425020 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 5338217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 1262626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1738. Min Range: -3.1738
Max Act: 3.0793. Min Act: -0.1700
Data Index: 4857519 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19