Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.6204. Min Act: -0.1700
Data Index: 1258777 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.5892. Min Act: -0.1700
Data Index: 973261 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.5579. Min Act: -0.1698
Data Index: 3236312 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.5267. Min Act: -0.1700
Data Index: 5848540 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.5267. Min Act: -0.1700
Data Index: 3515144 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4954. Min Act: -0.1700
Data Index: 116785 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4954. Min Act: -0.1700
Data Index: 1696165 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4954. Min Act: -0.1700
Data Index: 6014566 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4954. Min Act: -0.1700
Data Index: 1200520 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4642. Min Act: -0.1700
Data Index: 6132217 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4954. Min Act: -0.1700
Data Index: 8513278 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4642. Min Act: -0.1700
Data Index: 4167104 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4642. Min Act: -0.1700
Data Index: 7922244 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4642. Min Act: -0.1700
Data Index: 8442367 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4642. Min Act: -0.1700
Data Index: 733368 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4329. Min Act: -0.1700
Data Index: 1095893 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4329. Min Act: -0.1698
Data Index: 261496 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4329. Min Act: -0.1699
Data Index: 5755393 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4329. Min Act: -0.1696
Data Index: 3577990 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6204. Min Range: -4.6204
Max Act: 4.4329. Min Act: -0.1700
Data Index: 1997884 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19