Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4299 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1859. Min Range: -7.1859
Max Act: 7.1859. Min Act: -0.1700
Data Index: 2565687 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9984. Min Act: -0.1700
Data Index: 4581873 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.9047. Min Act: -0.1700
Data Index: 5914872 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.8109. Min Act: -0.1700
Data Index: 554524 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.7797. Min Act: -0.1700
Data Index: 1206820 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.7484. Min Act: -0.1700
Data Index: 3941277 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6859. Min Act: -0.1700
Data Index: 3169833 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.7172. Min Act: -0.1700
Data Index: 5490780 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6859. Min Act: -0.1700
Data Index: 4922423 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6859. Min Act: -0.1700
Data Index: 422827 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6859. Min Act: -0.1700
Data Index: 7215802 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6234. Min Act: -0.1700
Data Index: 4603262 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6547. Min Act: -0.1700
Data Index: 4837133 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6547. Min Act: -0.1700
Data Index: 5653347 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6547. Min Act: -0.1700
Data Index: 6782740 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6859. Min Act: -0.1700
Data Index: 687663 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6547. Min Act: -0.1700
Data Index: 6585151 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6547. Min Act: -0.1700
Data Index: 4126903 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6234. Min Act: -0.1700
Data Index: 2324955 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1859. Min Range: -7.1859
Max Act: 6.6234. Min Act: -0.1700
Data Index: 6582207 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19