Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5319 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.9203. Min Act: -0.1700
Data Index: 3504490 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.8891. Min Act: -0.1700
Data Index: 8439546 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.9203. Min Act: -0.1700
Data Index: 4786202 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.8891. Min Act: -0.1700
Data Index: 2022679 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.8266. Min Act: -0.1700
Data Index: 4257863 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.8578. Min Act: -0.1700
Data Index: 7011672 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.7953. Min Act: -0.1700
Data Index: 1373338 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.7328. Min Act: -0.1700
Data Index: 7223668 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.7328. Min Act: -0.1700
Data Index: 8521489 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.7016. Min Act: -0.1700
Data Index: 8074146 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.6391. Min Act: -0.1700
Data Index: 8351402 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.6391. Min Act: -0.1700
Data Index: 236903 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.6391. Min Act: -0.1700
Data Index: 8444912 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.6078. Min Act: -0.1700
Data Index: 2192094 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.6078. Min Act: -0.1700
Data Index: 5742230 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 20840 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 8763423 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.5453. Min Act: -0.1700
Data Index: 2075207 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.5453. Min Act: -0.1700
Data Index: 2125439 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9203. Min Range: -6.9203
Max Act: 6.5766. Min Act: -0.1700
Data Index: 3805442 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19