Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9848. Min Act: -0.1694
Data Index: 2404000 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0021. Min Range: -1.0021
Max Act: 1.0021. Min Act: -0.1700
Data Index: 5443044 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9848. Min Act: -0.1695
Data Index: 5007172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9848. Min Act: -0.1700
Data Index: 5948073 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9675. Min Act: -0.1681
Data Index: 6972329 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9675. Min Act: -0.1700
Data Index: 8044969 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9848. Min Act: -0.1700
Data Index: 1767462 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9848. Min Act: -0.1700
Data Index: 7152897 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1700
Data Index: 5906343 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1683
Data Index: 6803946 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1698
Data Index: 8471869 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1652
Data Index: 8400699 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1699
Data Index: 7980985 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1652
Data Index: 5280448 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1683
Data Index: 7038174 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1698
Data Index: 8120937 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9502. Min Act: -0.1700
Data Index: 4679861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9330. Min Act: -0.1700
Data Index: 2037659 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9330. Min Act: -0.1700
Data Index: 4920031 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0021. Min Range: -1.0021
Max Act: 0.9330. Min Act: -0.1698
Data Index: 2341226 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19