Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.2123. Min Act: -0.1700
Data Index: 3099625 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0873. Min Act: -0.1700
Data Index: 5973717 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9935. Min Act: -0.1700
Data Index: 1848524 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 5915670 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 1885090 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 6420339 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 7979174 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 6777650 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 8537803 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 7633309 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2123. Min Range: -7.2123
Max Act: 7.0248. Min Act: -0.1700
Data Index: 2579056 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 5024177 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9935. Min Act: -0.1700
Data Index: 1785892 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9935. Min Act: -0.1700
Data Index: 3138050 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9935. Min Act: -0.1700
Data Index: 454652 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 8379308 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 738320 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 7566455 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 5141733 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2123. Min Range: -7.2123
Max Act: 6.9623. Min Act: -0.1700
Data Index: 2918249 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19