Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.8714. Min Act: -0.1700
Data Index: 386237 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.8401. Min Act: -0.1700
Data Index: 7521701 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.8401. Min Act: -0.1700
Data Index: 7834121 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.7151. Min Act: -0.1700
Data Index: 6725350 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.7151. Min Act: -0.1700
Data Index: 5280713 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6839. Min Act: -0.1700
Data Index: 1731695 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6839. Min Act: -0.1700
Data Index: 8449108 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.7151. Min Act: -0.1700
Data Index: 1082939 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6839. Min Act: -0.1700
Data Index: 6315345 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6526. Min Act: -0.1700
Data Index: 6836581 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6526. Min Act: -0.1700
Data Index: 8533821 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6526. Min Act: -0.1700
Data Index: 6230748 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6526. Min Act: -0.1700
Data Index: 210237 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 6493200 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 2429228 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 4169031 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 5308686 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 7088947 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 2870386 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8714. Min Range: -4.8714
Max Act: 4.6214. Min Act: -0.1700
Data Index: 210238 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19