Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1938 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.2787. Min Act: -0.1700
Data Index: 1520038 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.1906. Min Act: -0.1700
Data Index: 6146561 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.0503. Min Act: -0.1700
Data Index: 939030 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.0242. Min Act: -0.1700
Data Index: 2567417 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.0155. Min Act: -0.1700
Data Index: 452874 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.0068. Min Act: -0.1700
Data Index: 3996190 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.0068. Min Act: -0.1700
Data Index: 3915238 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2787. Min Range: -1.2787
Max Act: 1.0068. Min Act: -0.1700
Data Index: 7834187 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9894. Min Act: -0.1700
Data Index: 3918446 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9808. Min Act: -0.1700
Data Index: 3352188 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9808. Min Act: -0.1700
Data Index: 1628831 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9808. Min Act: -0.1700
Data Index: 6214557 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9462. Min Act: -0.1700
Data Index: 4374673 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9635. Min Act: -0.1700
Data Index: 6221387 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9376. Min Act: -0.1700
Data Index: 3391699 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9548. Min Act: -0.1700
Data Index: 4454379 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9376. Min Act: -0.1700
Data Index: 5568002 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9376. Min Act: -0.1700
Data Index: 8137194 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9290. Min Act: -0.1700
Data Index: 5519618 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2787. Min Range: -1.2787
Max Act: 0.9290. Min Act: -0.1700
Data Index: 7335105 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19