Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.4348. Min Act: -0.1691
Data Index: 2178678 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.4084. Min Act: -0.1700
Data Index: 8415595 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3908. Min Act: -0.1699
Data Index: 1234929 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3908. Min Act: -0.1699
Data Index: 8013029 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3819. Min Act: -0.1700
Data Index: 901103 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3643. Min Act: -0.1700
Data Index: 3869045 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3731. Min Act: -0.1698
Data Index: 5856465 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3731. Min Act: -0.1699
Data Index: 4165601 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3643. Min Act: -0.1700
Data Index: 7569371 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3643. Min Act: -0.1700
Data Index: 4101223 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3555. Min Act: -0.1687
Data Index: 3155067 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3643. Min Act: -0.1606
Data Index: 3492679 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3643. Min Act: -0.1693
Data Index: 1521462 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3643. Min Act: -0.1700
Data Index: 6484411 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3555. Min Act: -0.1660
Data Index: 3836635 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3467. Min Act: -0.1700
Data Index: 2238403 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3555. Min Act: -0.1699
Data Index: 7209027 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3379. Min Act: -0.1700
Data Index: 1717115 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3467. Min Act: -0.1700
Data Index: 573669 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4348. Min Range: -1.4348
Max Act: 1.3379. Min Act: -0.1700
Data Index: 5584819 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19