Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.4188. Min Act: -0.1700
Data Index: 1103948 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.3250. Min Act: -0.1700
Data Index: 2214861 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.3250. Min Act: -0.1700
Data Index: 4997948 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.2313. Min Act: -0.1700
Data Index: 5338400 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.2313. Min Act: -0.1700
Data Index: 4334616 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.1688. Min Act: -0.1700
Data Index: 7190535 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.0750. Min Act: -0.1700
Data Index: 8391832 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.1062. Min Act: -0.1700
Data Index: 6606855 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.0437. Min Act: -0.1700
Data Index: 6062112 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.0750. Min Act: -0.1700
Data Index: 6180464 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.0125. Min Act: -0.1700
Data Index: 1103947 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4188. Min Range: -4.4188
Max Act: 4.0125. Min Act: -0.1700
Data Index: 4849814 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.9812. Min Act: -0.1700
Data Index: 1585412 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.9499. Min Act: -0.1700
Data Index: 5963553 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.9499. Min Act: -0.1700
Data Index: 7667602 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.9187. Min Act: -0.1700
Data Index: 2499832 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.9187. Min Act: -0.1700
Data Index: 5933049 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.9187. Min Act: -0.1700
Data Index: 6754344 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.8874. Min Act: -0.1700
Data Index: 6928204 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4188. Min Range: -4.4188
Max Act: 3.8874. Min Act: -0.1700
Data Index: 5067647 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19