Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.2989. Min Act: -0.1700
Data Index: 1506566 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.2052. Min Act: -0.1700
Data Index: 1169575 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.1427. Min Act: -0.1700
Data Index: 385457 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.1427. Min Act: -0.1700
Data Index: 2400660 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.1114. Min Act: -0.1700
Data Index: 261796 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.1427. Min Act: -0.1700
Data Index: 556698 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.0489. Min Act: -0.1700
Data Index: 873985 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2989. Min Range: -6.2989
Max Act: 6.0177. Min Act: -0.1700
Data Index: 3605475 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 5928056 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 2733956 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 2012938 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9864. Min Act: -0.1700
Data Index: 6042296 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 1302924 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9552. Min Act: -0.1700
Data Index: 4110537 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 3692127 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 2120906 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.8927. Min Act: -0.1700
Data Index: 3897274 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 7249882 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 6121682 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2989. Min Range: -6.2989
Max Act: 5.9239. Min Act: -0.1700
Data Index: 2133709 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19