Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.7829. Min Act: -0.1700
Data Index: 5882852 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.7204. Min Act: -0.1700
Data Index: 3430770 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.7204. Min Act: -0.1700
Data Index: 3486899 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.5329. Min Act: -0.1700
Data Index: 1252714 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.5642. Min Act: -0.1700
Data Index: 1104508 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.5329. Min Act: -0.1700
Data Index: 3605036 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.5017. Min Act: -0.1700
Data Index: 6256956 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.5017. Min Act: -0.1700
Data Index: 6622524 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4704. Min Act: -0.1700
Data Index: 299041 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4704. Min Act: -0.1700
Data Index: 5865758 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4704. Min Act: -0.1700
Data Index: 6384279 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4392. Min Act: -0.1700
Data Index: 3841930 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4079. Min Act: -0.1700
Data Index: 6599614 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4392. Min Act: -0.1700
Data Index: 5180933 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4079. Min Act: -0.1700
Data Index: 5316029 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.4392. Min Act: -0.1700
Data Index: 6971308 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.3767. Min Act: -0.1700
Data Index: 7129571 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.3767. Min Act: -0.1700
Data Index: 4206224 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.3767. Min Act: -0.1700
Data Index: 6973164 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7829. Min Range: -6.7829
Max Act: 6.3454. Min Act: -0.1700
Data Index: 6017357 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19