Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 164 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0251. Min Range: -4.0251
Max Act: 4.0251. Min Act: -0.1700
Data Index: 7998157 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9313. Min Act: -0.1700
Data Index: 7923967 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9625. Min Act: -0.1700
Data Index: 8641997 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8688. Min Act: -0.1700
Data Index: 42509 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 5335874 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 5287405 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 3818057 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8688. Min Act: -0.1700
Data Index: 3405215 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8062. Min Act: -0.1700
Data Index: 4085028 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 6122010 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 8130102 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8062. Min Act: -0.1700
Data Index: 7746008 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8062. Min Act: -0.1700
Data Index: 936553 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8062. Min Act: -0.1700
Data Index: 3818501 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.7749. Min Act: -0.1700
Data Index: 5700995 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8062. Min Act: -0.1700
Data Index: 6724902 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 6122009 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.7437. Min Act: -0.1700
Data Index: 2479611 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.7749. Min Act: -0.1700
Data Index: 957687 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.7437. Min Act: -0.1700
Data Index: 3046206 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19