Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4736 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1035. Min Range: -7.1035
Max Act: 7.1035. Min Act: -0.1700
Data Index: 400697 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1035. Min Range: -7.1035
Max Act: 7.0097. Min Act: -0.1700
Data Index: 645137 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.9160. Min Act: -0.1700
Data Index: 7815926 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.8847. Min Act: -0.1700
Data Index: 4998559 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.8222. Min Act: -0.1700
Data Index: 8466078 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.8222. Min Act: -0.1700
Data Index: 4300025 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.8222. Min Act: -0.1700
Data Index: 4314047 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.7910. Min Act: -0.1700
Data Index: 6298798 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.7910. Min Act: -0.1700
Data Index: 395507 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.7285. Min Act: -0.1700
Data Index: 3485263 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6972. Min Act: -0.1700
Data Index: 7336804 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6972. Min Act: -0.1700
Data Index: 4727339 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6972. Min Act: -0.1700
Data Index: 7481278 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6347. Min Act: -0.1700
Data Index: 5961382 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6660. Min Act: -0.1700
Data Index: 8667599 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6347. Min Act: -0.1700
Data Index: 6221194 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6347. Min Act: -0.1700
Data Index: 1675415 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6347. Min Act: -0.1700
Data Index: 6212884 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6347. Min Act: -0.1700
Data Index: 7468911 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1035. Min Range: -7.1035
Max Act: 6.6660. Min Act: -0.1700
Data Index: 8389592 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19