Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5606 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.4892. Min Act: -0.1700
Data Index: 1365675 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.4267. Min Act: -0.1700
Data Index: 269039 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.4267. Min Act: -0.1700
Data Index: 3281342 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.3954. Min Act: -0.1700
Data Index: 1209442 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.3017. Min Act: -0.1700
Data Index: 2930345 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.3017. Min Act: -0.1700
Data Index: 5022598 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.1454. Min Act: -0.1700
Data Index: 4504349 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.2079. Min Act: -0.1700
Data Index: 7864235 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.2079. Min Act: -0.1700
Data Index: 3101281 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.1142. Min Act: -0.1700
Data Index: 415111 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.1454. Min Act: -0.1700
Data Index: 4155074 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.1142. Min Act: -0.1700
Data Index: 946211 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0829. Min Act: -0.1700
Data Index: 8353179 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0829. Min Act: -0.1700
Data Index: 4436696 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0204. Min Act: -0.1700
Data Index: 6075033 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0517. Min Act: -0.1700
Data Index: 8353178 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0517. Min Act: -0.1700
Data Index: 3504643 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0204. Min Act: -0.1700
Data Index: 6760983 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4892. Min Range: -6.4892
Max Act: 6.0204. Min Act: -0.1700
Data Index: 3406623 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4892. Min Range: -6.4892
Max Act: 5.9892. Min Act: -0.1700
Data Index: 4780538 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19