Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4121 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 7160630 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.9011. Min Act: -0.1700
Data Index: 6030385 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7449. Min Act: -0.1700
Data Index: 7922567 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1659336 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6824. Min Act: -0.1700
Data Index: 8590409 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6824. Min Act: -0.1700
Data Index: 2941643 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6511. Min Act: -0.1700
Data Index: 6155203 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6824. Min Act: -0.1700
Data Index: 6081295 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6511. Min Act: -0.1700
Data Index: 6675965 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6511. Min Act: -0.1700
Data Index: 1487571 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6511. Min Act: -0.1700
Data Index: 7198696 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6511. Min Act: -0.1700
Data Index: 6030374 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 3868763 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 5048356 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 1911145 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 3521235 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 7401214 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 7416916 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6511. Min Act: -0.1700
Data Index: 6081277 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9636. Min Range: -4.9636
Max Act: 4.6199. Min Act: -0.1700
Data Index: 4375719 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19