Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.2981. Min Act: -0.1700
Data Index: 5762893 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.2668. Min Act: -0.1700
Data Index: 439575 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.2356. Min Act: -0.1700
Data Index: 1177119 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.1731. Min Act: -0.1700
Data Index: 6630094 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.1106. Min Act: -0.1700
Data Index: 1875385 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.0793. Min Act: -0.1700
Data Index: 7618730 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.0793. Min Act: -0.1700
Data Index: 2403063 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.0793. Min Act: -0.1700
Data Index: 2550068 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.0793. Min Act: -0.1700
Data Index: 4354176 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2981. Min Range: -5.2981
Max Act: 5.0168. Min Act: -0.1700
Data Index: 348320 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9856. Min Act: -0.1700
Data Index: 6775530 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9856. Min Act: -0.1700
Data Index: 7600473 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9856. Min Act: -0.1700
Data Index: 6387798 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9856. Min Act: -0.1700
Data Index: 5403565 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9543. Min Act: -0.1700
Data Index: 2273592 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9543. Min Act: -0.1700
Data Index: 3827891 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9231. Min Act: -0.1700
Data Index: 1583111 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9231. Min Act: -0.1700
Data Index: 2317076 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.8918. Min Act: -0.1700
Data Index: 653771 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2981. Min Range: -5.2981
Max Act: 4.9231. Min Act: -0.1700
Data Index: 5301313 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19