Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2510 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.4064. Min Act: -0.1700
Data Index: 8402306 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.4064. Min Act: -0.1700
Data Index: 2136557 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.2189. Min Act: -0.1700
Data Index: 5250900 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.1564. Min Act: -0.1700
Data Index: 2646208 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.1564. Min Act: -0.1700
Data Index: 8680474 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0939. Min Act: -0.1700
Data Index: 6414518 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0939. Min Act: -0.1700
Data Index: 755393 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0626. Min Act: -0.1700
Data Index: 7942479 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0626. Min Act: -0.1700
Data Index: 3103688 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0314. Min Act: -0.1700
Data Index: 8545540 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0314. Min Act: -0.1700
Data Index: 8609737 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0314. Min Act: -0.1698
Data Index: 3770835 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4064. Min Range: -7.4064
Max Act: 7.0001. Min Act: -0.1700
Data Index: 6953689 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9689. Min Act: -0.1700
Data Index: 4636465 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9689. Min Act: -0.1700
Data Index: 2245477 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9689. Min Act: -0.1700
Data Index: 5953232 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9689. Min Act: -0.1700
Data Index: 1674354 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9689. Min Act: -0.1700
Data Index: 5003858 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3695344 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4064. Min Range: -7.4064
Max Act: 6.9064. Min Act: -0.1700
Data Index: 7676561 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19