Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4796 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.6760. Min Act: -0.1700
Data Index: 2673206 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.5823. Min Act: -0.1700
Data Index: 1933507 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.5823. Min Act: -0.1700
Data Index: 6685145 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.5823. Min Act: -0.1700
Data Index: 8043464 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.4885. Min Act: -0.1700
Data Index: 6512045 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3948. Min Act: -0.1700
Data Index: 2499726 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3323. Min Act: -0.1700
Data Index: 2693788 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3323. Min Act: -0.1700
Data Index: 4599058 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3010. Min Act: -0.1700
Data Index: 272889 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1760. Min Act: -0.1700
Data Index: 2731281 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5145180 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1448. Min Act: -0.1700
Data Index: 2641612 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1448. Min Act: -0.1700
Data Index: 3202234 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1135. Min Act: -0.1700
Data Index: 897111 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5669176 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1135. Min Act: -0.1700
Data Index: 7915793 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0823. Min Act: -0.1700
Data Index: 2244938 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0823. Min Act: -0.1700
Data Index: 591641 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0510. Min Act: -0.1700
Data Index: 4287174 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0510. Min Act: -0.1700
Data Index: 4938538 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19