Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0041. Min Range: -6.0041
Max Act: 6.0041. Min Act: -0.1700
Data Index: 4167215 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.9103. Min Act: -0.1700
Data Index: 3732423 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.6916. Min Act: -0.1700
Data Index: 3742050 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.6603. Min Act: -0.1700
Data Index: 389400 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.5978. Min Act: -0.1700
Data Index: 8279888 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.5666. Min Act: -0.1700
Data Index: 6888949 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.5666. Min Act: -0.1700
Data Index: 2924930 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.5353. Min Act: -0.1700
Data Index: 4859979 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.5353. Min Act: -0.1700
Data Index: 1631508 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4728. Min Act: -0.1700
Data Index: 8263083 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.5041. Min Act: -0.1700
Data Index: 2106903 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4728. Min Act: -0.1700
Data Index: 2261176 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4103. Min Act: -0.1700
Data Index: 2139756 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4103. Min Act: -0.1700
Data Index: 3706581 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4103. Min Act: -0.1700
Data Index: 2443230 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4103. Min Act: -0.1700
Data Index: 3412115 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.3791. Min Act: -0.1700
Data Index: 5640015 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.4103. Min Act: -0.1700
Data Index: 4861100 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.3791. Min Act: -0.1700
Data Index: 147073 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0041. Min Range: -6.0041
Max Act: 5.3791. Min Act: -0.1700
Data Index: 5973334 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19