Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0325. Min Range: -3.0325
Max Act: 3.0325. Min Act: -0.1700
Data Index: 8825592 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9376. Min Act: -0.1700
Data Index: 441913 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9376. Min Act: -0.1700
Data Index: 417349 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9376. Min Act: -0.1700
Data Index: 3534764 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9376. Min Act: -0.1700
Data Index: 7748428 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9218. Min Act: -0.1700
Data Index: 3462548 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9218. Min Act: -0.1700
Data Index: 2151273 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8901. Min Act: -0.1700
Data Index: 2316904 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.9218. Min Act: -0.1700
Data Index: 400491 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8742. Min Act: -0.1700
Data Index: 4071968 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8424. Min Act: -0.1700
Data Index: 3138252 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8742. Min Act: -0.1700
Data Index: 8179022 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8583. Min Act: -0.1700
Data Index: 1589654 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8424. Min Act: -0.1700
Data Index: 1192450 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8424. Min Act: -0.1700
Data Index: 5872789 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8424. Min Act: -0.1700
Data Index: 8596156 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8424. Min Act: -0.1700
Data Index: 4144957 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8106. Min Act: -0.1700
Data Index: 2989816 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8265. Min Act: -0.1700
Data Index: 6366604 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0325. Min Range: -3.0325
Max Act: 2.8106. Min Act: -0.1700
Data Index: 5737864 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19