Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6325 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.6892. Min Act: -0.1700
Data Index: 3915698 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.5017. Min Act: -0.1700
Data Index: 5850297 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.4392. Min Act: -0.1700
Data Index: 8200460 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.3767. Min Act: -0.1700
Data Index: 3310075 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.3142. Min Act: -0.1700
Data Index: 7378845 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.2829. Min Act: -0.1700
Data Index: 843582 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.1267. Min Act: -0.1700
Data Index: 4915703 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.1267. Min Act: -0.1700
Data Index: 6591627 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.0954. Min Act: -0.1700
Data Index: 8005493 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.0642. Min Act: -0.1700
Data Index: 3629872 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.0642. Min Act: -0.1700
Data Index: 5640674 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.0329. Min Act: -0.1700
Data Index: 1615017 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.0329. Min Act: -0.1700
Data Index: 2911747 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6892. Min Range: -7.6892
Max Act: 7.0329. Min Act: -0.1700
Data Index: 826298 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6892. Min Range: -7.6892
Max Act: 6.9392. Min Act: -0.1700
Data Index: 2996850 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6892. Min Range: -7.6892
Max Act: 6.9079. Min Act: -0.1700
Data Index: 1464892 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6892. Min Range: -7.6892
Max Act: 6.8767. Min Act: -0.1700
Data Index: 1294695 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6892. Min Range: -7.6892
Max Act: 6.9079. Min Act: -0.1700
Data Index: 6234882 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6892. Min Range: -7.6892
Max Act: 6.8767. Min Act: -0.1700
Data Index: 2660404 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6892. Min Range: -7.6892
Max Act: 6.9079. Min Act: -0.1700
Data Index: 1668649 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19