Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.8322. Min Act: -0.1700
Data Index: 7175537 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.6447. Min Act: -0.1700
Data Index: 8406227 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.6447. Min Act: -0.1700
Data Index: 980607 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.6447. Min Act: -0.1700
Data Index: 771895 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.6135. Min Act: -0.1700
Data Index: 6005545 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.6135. Min Act: -0.1700
Data Index: 5584612 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.4260. Min Act: -0.1700
Data Index: 3067706 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.3635. Min Act: -0.1700
Data Index: 2605917 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.3322. Min Act: -0.1700
Data Index: 1011850 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.3322. Min Act: -0.1700
Data Index: 511090 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.3010. Min Act: -0.1700
Data Index: 3684358 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.3010. Min Act: -0.1700
Data Index: 6817116 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.1760. Min Act: -0.1700
Data Index: 3254479 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.1760. Min Act: -0.1700
Data Index: 6198917 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.1447. Min Act: -0.1700
Data Index: 8170380 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.1447. Min Act: -0.1700
Data Index: 4611588 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.0822. Min Act: -0.1700
Data Index: 5138484 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.1135. Min Act: -0.1700
Data Index: 5992132 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.0510. Min Act: -0.1700
Data Index: 422718 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8322. Min Range: -6.8322
Max Act: 6.0197. Min Act: -0.1700
Data Index: 5703411 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19