Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4761 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.5457. Min Act: -0.1700
Data Index: 508372 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.5144. Min Act: -0.1700
Data Index: 4538178 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.4207. Min Act: -0.1700
Data Index: 5666736 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.2332. Min Act: -0.1700
Data Index: 4538177 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.1707. Min Act: -0.1700
Data Index: 8254515 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.1707. Min Act: -0.1700
Data Index: 7033829 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.1082. Min Act: -0.1700
Data Index: 3252934 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.0769. Min Act: -0.1700
Data Index: 2900436 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.1082. Min Act: -0.1700
Data Index: 7765174 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.0769. Min Act: -0.1700
Data Index: 6610161 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.0769. Min Act: -0.1700
Data Index: 2855074 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.0457. Min Act: -0.1700
Data Index: 109466 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5457. Min Range: -6.5457
Max Act: 6.0144. Min Act: -0.1700
Data Index: 774158 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.9832. Min Act: -0.1700
Data Index: 3088997 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.9832. Min Act: -0.1700
Data Index: 1270794 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.9519. Min Act: -0.1700
Data Index: 4324052 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.9207. Min Act: -0.1700
Data Index: 1704754 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.9207. Min Act: -0.1700
Data Index: 8192087 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.8894. Min Act: -0.1700
Data Index: 1802008 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5457. Min Range: -6.5457
Max Act: 5.8894. Min Act: -0.1700
Data Index: 674869 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19