Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.4047. Min Range: -7.4047
Max Act: 7.4047. Min Act: -0.1700
Data Index: 355802 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4047. Min Range: -7.4047
Max Act: 7.1547. Min Act: -0.1700
Data Index: 6854716 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4047. Min Range: -7.4047
Max Act: 7.0922. Min Act: -0.1700
Data Index: 4215904 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4047. Min Range: -7.4047
Max Act: 7.0610. Min Act: -0.1700
Data Index: 1392509 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4047. Min Range: -7.4047
Max Act: 7.0297. Min Act: -0.1700
Data Index: 3544452 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9985. Min Act: -0.1700
Data Index: 3341596 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9672. Min Act: -0.1700
Data Index: 1692869 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9672. Min Act: -0.1700
Data Index: 8363384 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9672. Min Act: -0.1700
Data Index: 5647698 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9360. Min Act: -0.1700
Data Index: 4715249 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9672. Min Act: -0.1700
Data Index: 2150873 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9672. Min Act: -0.1700
Data Index: 1788909 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.8735. Min Act: -0.1700
Data Index: 6747660 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.8735. Min Act: -0.1700
Data Index: 5659675 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.8735. Min Act: -0.1700
Data Index: 214371 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.9360. Min Act: -0.1700
Data Index: 5876939 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.8110. Min Act: -0.1700
Data Index: 8280676 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.8422. Min Act: -0.1700
Data Index: 3379201 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.8110. Min Act: -0.1700
Data Index: 4391777 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4047. Min Range: -7.4047
Max Act: 6.7797. Min Act: -0.1700
Data Index: 3117716 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19