Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0855. Min Range: -7.0855
Max Act: 7.0855. Min Act: -0.1700
Data Index: 8143692 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.9292. Min Act: -0.1700
Data Index: 1415326 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.9292. Min Act: -0.1700
Data Index: 3701193 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.9292. Min Act: -0.1700
Data Index: 5176387 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.8980. Min Act: -0.1700
Data Index: 330821 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.9292. Min Act: -0.1700
Data Index: 2548742 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.8667. Min Act: -0.1700
Data Index: 8350591 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.8042. Min Act: -0.1700
Data Index: 921649 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7730. Min Act: -0.1700
Data Index: 4179020 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7730. Min Act: -0.1700
Data Index: 921660 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7730. Min Act: -0.1700
Data Index: 8671993 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7417. Min Act: -0.1700
Data Index: 779081 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7417. Min Act: -0.1700
Data Index: 3894544 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7417. Min Act: -0.1700
Data Index: 797721 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.7105. Min Act: -0.1700
Data Index: 2507328 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.6792. Min Act: -0.1700
Data Index: 5352074 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.6480. Min Act: -0.1700
Data Index: 8671992 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.6480. Min Act: -0.1700
Data Index: 3787590 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.6480. Min Act: -0.1700
Data Index: 6251046 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0855. Min Range: -7.0855
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6779376 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19