Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2364 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1015. Min Range: -6.1015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 738321 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1015. Min Range: -6.1015
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3228034 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.9453. Min Act: -0.1700
Data Index: 8154164 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.9453. Min Act: -0.1700
Data Index: 3008849 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.9453. Min Act: -0.1700
Data Index: 5474507 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.9140. Min Act: -0.1700
Data Index: 7606556 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.9453. Min Act: -0.1700
Data Index: 3034976 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.8203. Min Act: -0.1700
Data Index: 7630372 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.8515. Min Act: -0.1700
Data Index: 7945074 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.8203. Min Act: -0.1700
Data Index: 1285692 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.8203. Min Act: -0.1700
Data Index: 2012668 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.8203. Min Act: -0.1700
Data Index: 7523152 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6702759 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7578. Min Act: -0.1700
Data Index: 5026134 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7265. Min Act: -0.1700
Data Index: 3215125 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7265. Min Act: -0.1700
Data Index: 2320588 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7265. Min Act: -0.1700
Data Index: 4561973 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.6953. Min Act: -0.1700
Data Index: 4896365 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7265. Min Act: -0.1700
Data Index: 6655072 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1015. Min Range: -6.1015
Max Act: 5.7265. Min Act: -0.1700
Data Index: 6844327 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19