Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1488 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0392. Min Range: -1.0392
Max Act: 1.0392. Min Act: -0.1700
Data Index: 8158769 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0392. Min Range: -1.0392
Max Act: 1.0044. Min Act: -0.1700
Data Index: 1822183 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9870. Min Act: -0.1700
Data Index: 1792609 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9697. Min Act: -0.1699
Data Index: 3322915 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9870. Min Act: -0.1700
Data Index: 4558935 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9524. Min Act: -0.1696
Data Index: 6506129 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9697. Min Act: -0.1700
Data Index: 3826033 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9524. Min Act: -0.1700
Data Index: 5175232 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9524. Min Act: -0.1700
Data Index: 5993306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9266. Min Act: -0.1697
Data Index: 610990 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9180. Min Act: -0.1700
Data Index: 1698196 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9266. Min Act: -0.1699
Data Index: 6188892 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9352. Min Act: -0.1700
Data Index: 7520535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9266. Min Act: -0.1700
Data Index: 4124585 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9266. Min Act: -0.1700
Data Index: 7538211 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9180. Min Act: -0.1685
Data Index: 6944844 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9180. Min Act: -0.1700
Data Index: 5362739 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9095. Min Act: -0.1700
Data Index: 1235804 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.9180. Min Act: -0.1700
Data Index: 1106084 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0392. Min Range: -1.0392
Max Act: 0.8923. Min Act: -0.1699
Data Index: 5795477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19