Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5796. Min Act: -0.1700
Data Index: 1680054 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5483. Min Act: -0.1700
Data Index: 8768503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5483. Min Act: -0.1700
Data Index: 6943993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5483. Min Act: -0.1700
Data Index: 4474840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5483. Min Act: -0.1700
Data Index: 7934466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5170. Min Act: -0.1700
Data Index: 7976564 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5170. Min Act: -0.1700
Data Index: 3246933 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 900674 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4575399 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4563631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4472410 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4454728 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 3760552 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 1895874 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 3749616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 121382 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 1854880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 3194058 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.5170. Min Act: -0.1700
Data Index: 2850183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5796. Min Range: -3.5796
Max Act: 3.4857. Min Act: -0.1700
Data Index: 2783645 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19