Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0795. Min Range: -4.0795
Max Act: 4.0795. Min Act: -0.1700
Data Index: 5899900 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.9857. Min Act: -0.1700
Data Index: 317170 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.9857. Min Act: -0.1700
Data Index: 4542542 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.9544. Min Act: -0.1700
Data Index: 3081431 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.9544. Min Act: -0.1700
Data Index: 5899891 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.9544. Min Act: -0.1700
Data Index: 5899890 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8919. Min Act: -0.1700
Data Index: 4951314 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8919. Min Act: -0.1700
Data Index: 4648932 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.9232. Min Act: -0.1697
Data Index: 6278644 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8919. Min Act: -0.1700
Data Index: 4064153 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8606. Min Act: -0.1700
Data Index: 7399044 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8606. Min Act: -0.1700
Data Index: 5436722 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8919. Min Act: -0.1700
Data Index: 6278643 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8294. Min Act: -0.1700
Data Index: 4648924 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.7981. Min Act: -0.1699
Data Index: 4064156 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.8606. Min Act: -0.1700
Data Index: 5899892 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.7668. Min Act: -0.1700
Data Index: 2192836 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.7512. Min Act: -0.1700
Data Index: 5436712 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.7512. Min Act: -0.1700
Data Index: 4142711 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0795. Min Range: -4.0795
Max Act: 3.7199. Min Act: -0.1700
Data Index: 4542541 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19