Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0291. Min Range: -5.0291
Max Act: 5.0291. Min Act: -0.1700
Data Index: 1041919 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.7166. Min Act: -0.1700
Data Index: 8610631 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.6541. Min Act: -0.1700
Data Index: 5654502 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.6541. Min Act: -0.1700
Data Index: 7795015 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.5291. Min Act: -0.1700
Data Index: 1375692 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.5291. Min Act: -0.1700
Data Index: 6192232 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.5291. Min Act: -0.1700
Data Index: 4659982 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.5291. Min Act: -0.1700
Data Index: 7996504 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.5291. Min Act: -0.1700
Data Index: 4384332 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.4979. Min Act: -0.1700
Data Index: 5657057 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.4979. Min Act: -0.1700
Data Index: 5404010 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.4354. Min Act: -0.1700
Data Index: 4144471 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.4354. Min Act: -0.1700
Data Index: 930385 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.3729. Min Act: -0.1700
Data Index: 8034616 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.3729. Min Act: -0.1700
Data Index: 2979721 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.3729. Min Act: -0.1700
Data Index: 3781795 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.3729. Min Act: -0.1700
Data Index: 802373 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.4041. Min Act: -0.1700
Data Index: 6935029 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.3416. Min Act: -0.1700
Data Index: 6358567 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0291. Min Range: -5.0291
Max Act: 4.3416. Min Act: -0.1700
Data Index: 6934860 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19