Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5113 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.5492. Min Act: -0.1700
Data Index: 4809890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.5492. Min Act: -0.1700
Data Index: 4434189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.5492. Min Act: -0.1700
Data Index: 8030910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.5180. Min Act: -0.1700
Data Index: 2808621 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 710627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 6213217 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 4517553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 6763264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 7258710 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 7957563 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4867. Min Act: -0.1700
Data Index: 877094 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 5519872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 8218510 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 7625421 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 7377323 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 6652965 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 6591252 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4555. Min Act: -0.1700
Data Index: 5623159 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4242. Min Act: -0.1700
Data Index: 4482278 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5492. Min Range: -4.5492
Max Act: 4.4242. Min Act: -0.1700
Data Index: 2553361 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19