Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0731. Min Range: -6.0731
Max Act: 6.0731. Min Act: -0.1700
Data Index: 5842621 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.8856. Min Act: -0.1700
Data Index: 4505814 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.8231. Min Act: -0.1700
Data Index: 4505813 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.6981. Min Act: -0.1700
Data Index: 3816374 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.6981. Min Act: -0.1700
Data Index: 2694358 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.6044. Min Act: -0.1700
Data Index: 3816375 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.5731. Min Act: -0.1700
Data Index: 4505812 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4794. Min Act: -0.1700
Data Index: 2802893 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4794. Min Act: -0.1700
Data Index: 4261190 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4794. Min Act: -0.1700
Data Index: 2965432 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4794. Min Act: -0.1700
Data Index: 6518887 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4794. Min Act: -0.1700
Data Index: 4687346 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4481. Min Act: -0.1700
Data Index: 4046608 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4169. Min Act: -0.1700
Data Index: 8785221 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4169. Min Act: -0.1700
Data Index: 3405945 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4481. Min Act: -0.1700
Data Index: 1715194 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4481. Min Act: -0.1700
Data Index: 2452514 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4169. Min Act: -0.1700
Data Index: 2917446 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4169. Min Act: -0.1700
Data Index: 354590 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0731. Min Range: -6.0731
Max Act: 5.4169. Min Act: -0.1700
Data Index: 6107647 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19