Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.1974. Min Act: -0.1700
Data Index: 5442303 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.1037. Min Act: -0.1700
Data Index: 4156088 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.0099. Min Act: -0.1700
Data Index: 1326190 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.0412. Min Act: -0.1700
Data Index: 1544153 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9786. Min Act: -0.1700
Data Index: 739241 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1974. Min Range: -4.1974
Max Act: 4.0099. Min Act: -0.1700
Data Index: 6479932 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9786. Min Act: -0.1700
Data Index: 2837446 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9786. Min Act: -0.1700
Data Index: 7891212 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9474. Min Act: -0.1700
Data Index: 63423 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.9161. Min Act: -0.1700
Data Index: 4810259 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8848. Min Act: -0.1700
Data Index: 7803670 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8536. Min Act: -0.1700
Data Index: 6223630 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8379. Min Act: -0.1700
Data Index: 7837217 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8379. Min Act: -0.1700
Data Index: 964396 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8379. Min Act: -0.1700
Data Index: 8311447 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8223. Min Act: -0.1700
Data Index: 4970833 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4656911 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4879502 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.7910. Min Act: -0.1700
Data Index: 1119197 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1974. Min Range: -4.1974
Max Act: 3.7910. Min Act: -0.1700
Data Index: 2353903 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19