Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.1454. Min Act: -0.1700
Data Index: 6727550 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1454. Min Range: -4.1454
Max Act: 4.0829. Min Act: -0.1700
Data Index: 2811456 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9891. Min Act: -0.1700
Data Index: 5439480 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.9891. Min Act: -0.1700
Data Index: 2324913 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.8484. Min Act: -0.1700
Data Index: 7953155 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.8171. Min Act: -0.1700
Data Index: 6567331 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.8328. Min Act: -0.1700
Data Index: 4954440 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.8171. Min Act: -0.1700
Data Index: 3684347 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.7546. Min Act: -0.1700
Data Index: 3604006 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.7389. Min Act: -0.1700
Data Index: 7779202 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.7233. Min Act: -0.1700
Data Index: 698288 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.7233. Min Act: -0.1700
Data Index: 6207879 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.7077. Min Act: -0.1700
Data Index: 2007599 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.7077. Min Act: -0.1700
Data Index: 5101957 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.6451. Min Act: -0.1700
Data Index: 6468422 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.6294. Min Act: -0.1700
Data Index: 1456888 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.6294. Min Act: -0.1700
Data Index: 3926617 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.6294. Min Act: -0.1700
Data Index: 1870992 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7206066 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1454. Min Range: -4.1454
Max Act: 3.6138. Min Act: -0.1700
Data Index: 2235272 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19