Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.3875. Min Act: -0.1700
Data Index: 3740548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.2200. Min Act: -0.1700
Data Index: 6956502 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.2112. Min Act: -0.1700
Data Index: 3388037 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.2024. Min Act: -0.1700
Data Index: 2226559 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1760. Min Act: -0.1700
Data Index: 6895304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1760. Min Act: -0.1700
Data Index: 5778480 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 7312491 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 4112757 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 1726758 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 2149293 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1496. Min Act: -0.1700
Data Index: 1982915 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 5017926 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 7220022 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1584. Min Act: -0.1700
Data Index: 3922595 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1496. Min Act: -0.1700
Data Index: 8011870 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1496. Min Act: -0.1700
Data Index: 280546 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1496. Min Act: -0.1700
Data Index: 1553074 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1320. Min Act: -0.1700
Data Index: 1861061 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1320. Min Act: -0.1700
Data Index: 1607005 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3875. Min Range: -1.3875
Max Act: 1.1320. Min Act: -0.1700
Data Index: 7313774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19