Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.7273. Min Act: -0.1700
Data Index: 6031857 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.6804. Min Act: -0.1700
Data Index: 5829598 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.7117. Min Act: -0.1700
Data Index: 2231599 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.6648. Min Act: -0.1700
Data Index: 7542259 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5865. Min Act: -0.1700
Data Index: 3446028 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.6022. Min Act: -0.1700
Data Index: 2992324 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5709. Min Act: -0.1700
Data Index: 2073017 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5552. Min Act: -0.1700
Data Index: 354453 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5865. Min Act: -0.1700
Data Index: 7793627 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5709. Min Act: -0.1700
Data Index: 2266060 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5239. Min Act: -0.1700
Data Index: 5859165 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5239. Min Act: -0.1700
Data Index: 2578802 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5082. Min Act: -0.1700
Data Index: 505605 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5082. Min Act: -0.1700
Data Index: 1836119 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5239. Min Act: -0.1700
Data Index: 7541278 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5239. Min Act: -0.1700
Data Index: 3587784 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5082. Min Act: -0.1700
Data Index: 5222795 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5082. Min Act: -0.1700
Data Index: 647656 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.4926. Min Act: -0.1700
Data Index: 5570176 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7273. Min Range: -3.7273
Max Act: 3.5239. Min Act: -0.1700
Data Index: 2782160 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19