Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2405. Min Range: -5.2405
Max Act: 5.2405. Min Act: -0.1700
Data Index: 3457790 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2405. Min Range: -5.2405
Max Act: 5.1780. Min Act: -0.1700
Data Index: 8829223 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2405. Min Range: -5.2405
Max Act: 5.0843. Min Act: -0.1700
Data Index: 4089591 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2405. Min Range: -5.2405
Max Act: 5.0530. Min Act: -0.1700
Data Index: 8718824 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9905. Min Act: -0.1700
Data Index: 8587089 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9593. Min Act: -0.1700
Data Index: 3782623 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9905. Min Act: -0.1700
Data Index: 3102660 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9905. Min Act: -0.1700
Data Index: 3693225 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9905. Min Act: -0.1700
Data Index: 6617966 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9593. Min Act: -0.1700
Data Index: 6377866 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8968. Min Act: -0.1700
Data Index: 6099978 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9280. Min Act: -0.1700
Data Index: 6670811 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8968. Min Act: -0.1700
Data Index: 7887220 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8968. Min Act: -0.1700
Data Index: 6075176 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8968. Min Act: -0.1700
Data Index: 231218 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.9280. Min Act: -0.1700
Data Index: 5678940 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8655. Min Act: -0.1700
Data Index: 4369777 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8655. Min Act: -0.1700
Data Index: 1274486 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8655. Min Act: -0.1700
Data Index: 6240079 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2405. Min Range: -5.2405
Max Act: 4.8343. Min Act: -0.1700
Data Index: 2727232 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19