Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1879 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.8342. Min Act: -0.1700
Data Index: 6986700 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.8342. Min Act: -0.1700
Data Index: 3402822 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.8342. Min Act: -0.1700
Data Index: 6379072 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.7717. Min Act: -0.1700
Data Index: 8343077 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.6780. Min Act: -0.1700
Data Index: 3186144 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.5842. Min Act: -0.1700
Data Index: 8680113 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.5217. Min Act: -0.1700
Data Index: 8016877 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4905. Min Act: -0.1700
Data Index: 206171 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4905. Min Act: -0.1700
Data Index: 1884620 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4905. Min Act: -0.1700
Data Index: 4243549 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4905. Min Act: -0.1700
Data Index: 3434034 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4905. Min Act: -0.1700
Data Index: 7832050 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4280. Min Act: -0.1700
Data Index: 443448 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.4280. Min Act: -0.1700
Data Index: 3657174 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.3967. Min Act: -0.1700
Data Index: 2321442 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.3655. Min Act: -0.1700
Data Index: 3845305 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.3342. Min Act: -0.1700
Data Index: 2557501 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.3342. Min Act: -0.1700
Data Index: 2000446 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.3030. Min Act: -0.1700
Data Index: 3803762 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8342. Min Range: -5.8342
Max Act: 5.3030. Min Act: -0.1700
Data Index: 8054277 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19