Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8654. Min Act: -0.1700
Data Index: 715043 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8654. Min Act: -0.1700
Data Index: 8705442 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8654. Min Act: -0.1700
Data Index: 3159001 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8029. Min Act: -0.1700
Data Index: 1551397 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8029. Min Act: -0.1700
Data Index: 5340635 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8029. Min Act: -0.1700
Data Index: 6621208 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.8029. Min Act: -0.1700
Data Index: 4377798 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.7716. Min Act: -0.1700
Data Index: 2258827 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.7716. Min Act: -0.1700
Data Index: 3886478 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.7716. Min Act: -0.1700
Data Index: 121441 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.7091. Min Act: -0.1700
Data Index: 6170641 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.7404. Min Act: -0.1700
Data Index: 8496195 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.7091. Min Act: -0.1700
Data Index: 6460662 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.6466. Min Act: -0.1700
Data Index: 3143428 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.6779. Min Act: -0.1700
Data Index: 389127 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.6466. Min Act: -0.1700
Data Index: 5222264 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.6154. Min Act: -0.1700
Data Index: 1211499 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.5841. Min Act: -0.1700
Data Index: 829774 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.6154. Min Act: -0.1700
Data Index: 7711419 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8654. Min Range: -7.8654
Max Act: 7.6154. Min Act: -0.1700
Data Index: 2551136 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19