Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.7107. Min Act: -0.1699
Data Index: 8210281 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.5857. Min Act: -0.1700
Data Index: 2984386 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.5232. Min Act: -0.1700
Data Index: 7252480 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.3357. Min Act: -0.1700
Data Index: 5433337 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.2732. Min Act: -0.1700
Data Index: 4673193 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.1170. Min Act: -0.1700
Data Index: 6196328 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.0857. Min Act: -0.1700
Data Index: 2383195 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.0545. Min Act: -0.1700
Data Index: 1106113 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7107. Min Range: -7.7107
Max Act: 7.0232. Min Act: -0.1700
Data Index: 2815950 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.9920. Min Act: -0.1700
Data Index: 7264354 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.9920. Min Act: -0.1700
Data Index: 5166820 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.9607. Min Act: -0.1700
Data Index: 8697052 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.9295. Min Act: -0.1700
Data Index: 6223355 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8982. Min Act: -0.1700
Data Index: 5641137 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8982. Min Act: -0.1700
Data Index: 8711147 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8982. Min Act: -0.1700
Data Index: 304496 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8982. Min Act: -0.1700
Data Index: 3702536 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8670. Min Act: -0.1700
Data Index: 3853172 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8357. Min Act: -0.1700
Data Index: 27022 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7107. Min Range: -7.7107
Max Act: 6.8670. Min Act: -0.1700
Data Index: 6663198 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19