Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1688 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.9617. Min Act: -0.1700
Data Index: 1229593 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.3367. Min Act: -0.1700
Data Index: 5185592 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.2742. Min Act: -0.1700
Data Index: 906941 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.1804. Min Act: -0.1700
Data Index: 945293 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.1492. Min Act: -0.1700
Data Index: 2248923 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0867. Min Act: -0.1700
Data Index: 1996180 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0554. Min Act: -0.1700
Data Index: 2530872 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0867. Min Act: -0.1700
Data Index: 5523054 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0242. Min Act: -0.1700
Data Index: 8536092 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0554. Min Act: -0.1700
Data Index: 2011969 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0554. Min Act: -0.1700
Data Index: 249765 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0242. Min Act: -0.1700
Data Index: 7155902 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0554. Min Act: -0.1700
Data Index: 7366699 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0554. Min Act: -0.1700
Data Index: 3366553 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9617. Min Range: -7.9617
Max Act: 7.0242. Min Act: -0.1700
Data Index: 107736 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9617. Min Range: -7.9617
Max Act: 6.9929. Min Act: -0.1700
Data Index: 8074295 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9617. Min Range: -7.9617
Max Act: 6.9929. Min Act: -0.1700
Data Index: 3323464 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9617. Min Range: -7.9617
Max Act: 6.9929. Min Act: -0.1700
Data Index: 4053364 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9617. Min Range: -7.9617
Max Act: 6.9929. Min Act: -0.1700
Data Index: 8214715 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9617. Min Range: -7.9617
Max Act: 6.9617. Min Act: -0.1700
Data Index: 976878 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19