Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6509. Min Act: -0.1700
Data Index: 3589346 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6669. Min Act: -0.1700
Data Index: 3917755 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6669. Min Act: -0.1700
Data Index: 8024959 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6348. Min Act: -0.1700
Data Index: 7292893 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6509. Min Act: -0.1700
Data Index: 6605395 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6348. Min Act: -0.1700
Data Index: 5972270 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6348. Min Act: -0.1700
Data Index: 7751295 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6027. Min Act: -0.1700
Data Index: 6757669 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5866. Min Act: -0.1700
Data Index: 6903500 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.6187. Min Act: -0.1700
Data Index: 3839382 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5866. Min Act: -0.1700
Data Index: 5018419 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5866. Min Act: -0.1700
Data Index: 836461 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5704. Min Act: -0.1700
Data Index: 3854099 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5543. Min Act: -0.1700
Data Index: 3583363 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5543. Min Act: -0.1700
Data Index: 4918427 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5704. Min Act: -0.1700
Data Index: 3097666 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5704. Min Act: -0.1700
Data Index: 3591816 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5704. Min Act: -0.1700
Data Index: 5751407 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5543. Min Act: -0.1700
Data Index: 1238858 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6669. Min Range: -2.6669
Max Act: 2.5543. Min Act: -0.1700
Data Index: 4427275 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19