Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4536 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.9774. Min Act: -0.1700
Data Index: 8648602 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.7899. Min Act: -0.1700
Data Index: 5159633 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.7274. Min Act: -0.1700
Data Index: 8525657 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.6962. Min Act: -0.1700
Data Index: 185560 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.6337. Min Act: -0.1700
Data Index: 2201110 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.6024. Min Act: -0.1700
Data Index: 426941 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.6024. Min Act: -0.1700
Data Index: 5090324 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.5087. Min Act: -0.1700
Data Index: 3537312 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.5399. Min Act: -0.1700
Data Index: 3727273 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.5399. Min Act: -0.1700
Data Index: 3719378 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.5087. Min Act: -0.1700
Data Index: 4667699 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.4149. Min Act: -0.1700
Data Index: 3258848 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3837. Min Act: -0.1700
Data Index: 7411135 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3837. Min Act: -0.1700
Data Index: 1715008 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3837. Min Act: -0.1700
Data Index: 3669304 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3837. Min Act: -0.1700
Data Index: 3441520 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3524. Min Act: -0.1700
Data Index: 7214366 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3524. Min Act: -0.1700
Data Index: 3325074 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.3212. Min Act: -0.1700
Data Index: 2771457 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9774. Min Range: -6.9774
Max Act: 6.2899. Min Act: -0.1700
Data Index: 4848939 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19