Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4375 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.7204. Min Act: -0.1700
Data Index: 1472332 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.6892. Min Act: -0.1700
Data Index: 2739339 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.6579. Min Act: -0.1700
Data Index: 4346798 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.5016. Min Act: -0.1700
Data Index: 4683388 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.4079. Min Act: -0.1700
Data Index: 5072938 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.3766. Min Act: -0.1700
Data Index: 3587033 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.3454. Min Act: -0.1700
Data Index: 3123385 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.3454. Min Act: -0.1700
Data Index: 4726403 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.3454. Min Act: -0.1700
Data Index: 7192392 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.3454. Min Act: -0.1700
Data Index: 7462801 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.3141. Min Act: -0.1700
Data Index: 2668860 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.2829. Min Act: -0.1700
Data Index: 5290054 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.2829. Min Act: -0.1700
Data Index: 4172729 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.2516. Min Act: -0.1700
Data Index: 4270046 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.2516. Min Act: -0.1700
Data Index: 4896857 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.2204. Min Act: -0.1700
Data Index: 6672502 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.1891. Min Act: -0.1700
Data Index: 8711891 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.1891. Min Act: -0.1700
Data Index: 1472324 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.1891. Min Act: -0.1700
Data Index: 1356796 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7204. Min Range: -4.7204
Max Act: 4.1579. Min Act: -0.1700
Data Index: 1973525 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19