Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 208 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.3929. Min Range: -8.3929
Max Act: 8.3929. Min Act: -0.1700
Data Index: 7480264 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3929. Min Range: -8.3929
Max Act: 8.0179. Min Act: -0.1700
Data Index: 5893615 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3929. Min Range: -8.3929
Max Act: 7.5179. Min Act: -0.1700
Data Index: 5781596 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3929. Min Range: -8.3929
Max Act: 7.2992. Min Act: -0.1695
Data Index: 1195984 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3929. Min Range: -8.3929
Max Act: 7.1117. Min Act: -0.1700
Data Index: 5304175 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3929. Min Range: -8.3929
Max Act: 7.0179. Min Act: -0.1699
Data Index: 861773 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.8617. Min Act: -0.1698
Data Index: 3325345 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3929. Min Range: -8.3929
Max Act: 7.0492. Min Act: -0.1692
Data Index: 1864316 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.8304. Min Act: -0.1700
Data Index: 4328523 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.7992. Min Act: -0.1700
Data Index: 2596956 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6965486 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.8617. Min Act: -0.1700
Data Index: 3190548 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.7054. Min Act: -0.1700
Data Index: 1690761 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.7367. Min Act: -0.1700
Data Index: 1781045 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.6117. Min Act: -0.1700
Data Index: 2650651 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.6429. Min Act: -0.1700
Data Index: 6028415 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.3617. Min Act: -0.1700
Data Index: 6854040 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.4554. Min Act: -0.1699
Data Index: 8558126 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.4242. Min Act: -0.1700
Data Index: 6673211 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3929. Min Range: -8.3929
Max Act: 6.4242. Min Act: -0.1700
Data Index: 1918140 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19