Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1864 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9109. Min Range: -8.9109
Max Act: 8.9109. Min Act: -0.1700
Data Index: 5242787 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9109. Min Range: -8.9109
Max Act: 8.3484. Min Act: -0.1700
Data Index: 3789485 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9109. Min Range: -8.9109
Max Act: 8.2859. Min Act: -0.1700
Data Index: 5627916 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9109. Min Range: -8.9109
Max Act: 8.2859. Min Act: -0.1700
Data Index: 1242164 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9109. Min Range: -8.9109
Max Act: 8.2234. Min Act: -0.1700
Data Index: 1125948 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9109. Min Range: -8.9109
Max Act: 8.0984. Min Act: -0.1700
Data Index: 5001140 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.9734. Min Act: -0.1700
Data Index: 7758954 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.9109. Min Act: -0.1700
Data Index: 4880011 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.9109. Min Act: -0.1700
Data Index: 7458862 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 8323616 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 723092 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.7234. Min Act: -0.1700
Data Index: 4467904 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.7234. Min Act: -0.1700
Data Index: 691039 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 811532 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.7234. Min Act: -0.1700
Data Index: 163756 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.6609. Min Act: -0.1700
Data Index: 670648 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.6609. Min Act: -0.1700
Data Index: 2649390 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.6609. Min Act: -0.1700
Data Index: 6888911 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.5984. Min Act: -0.1700
Data Index: 1059110 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9109. Min Range: -8.9109
Max Act: 7.5359. Min Act: -0.1700
Data Index: 1755931 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19