Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1608. Min Act: -0.1700
Data Index: 7210403 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1923. Min Act: -0.1700
Data Index: 842306 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1608. Min Act: -0.1700
Data Index: 7478747 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1293. Min Act: -0.1700
Data Index: 7363216 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1293. Min Act: -0.1700
Data Index: 7106717 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 2749841 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1293. Min Act: -0.1700
Data Index: 5798958 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.1293. Min Act: -0.1700
Data Index: 4043313 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 5429379 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 4891079 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 5841887 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0663. Min Act: -0.1700
Data Index: 5940275 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 294601 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 6232562 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 6398576 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 6464113 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 6995341 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 7088836 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 2742986 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1923. Min Range: -3.1923
Max Act: 3.0978. Min Act: -0.1700
Data Index: 3445610 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19