Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2068. Min Range: -4.2068
Max Act: 4.2068. Min Act: -0.1700
Data Index: 909133 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2068. Min Range: -4.2068
Max Act: 4.0193. Min Act: -0.1700
Data Index: 6258046 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8942. Min Act: -0.1700
Data Index: 6089980 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8630. Min Act: -0.1700
Data Index: 2772104 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8317. Min Act: -0.1700
Data Index: 7543685 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8317. Min Act: -0.1700
Data Index: 4406791 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8004. Min Act: -0.1700
Data Index: 1252321 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8004. Min Act: -0.1700
Data Index: 5997579 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.8004. Min Act: -0.1700
Data Index: 5771809 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7691. Min Act: -0.1700
Data Index: 7214048 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7691. Min Act: -0.1700
Data Index: 6671980 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7535. Min Act: -0.1700
Data Index: 6432550 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7691. Min Act: -0.1700
Data Index: 2782791 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7691. Min Act: -0.1700
Data Index: 8788549 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7691. Min Act: -0.1700
Data Index: 5977447 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7535. Min Act: -0.1700
Data Index: 6311769 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7535. Min Act: -0.1700
Data Index: 3199864 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7535. Min Act: -0.1700
Data Index: 1561960 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7535. Min Act: -0.1700
Data Index: 4466544 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2068. Min Range: -4.2068
Max Act: 3.7691. Min Act: -0.1700
Data Index: 3766509 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19