Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1415 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.7598. Min Act: -0.1700
Data Index: 1720096 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.7129. Min Act: -0.1700
Data Index: 7658846 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.6346. Min Act: -0.1700
Data Index: 6449056 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.6033. Min Act: -0.1700
Data Index: 8045218 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5564. Min Act: -0.1700
Data Index: 8058976 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5877. Min Act: -0.1700
Data Index: 3633495 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5720. Min Act: -0.1700
Data Index: 1227855 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5407. Min Act: -0.1700
Data Index: 8056383 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5251. Min Act: -0.1700
Data Index: 6662201 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5564. Min Act: -0.1700
Data Index: 360787 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5094. Min Act: -0.1700
Data Index: 7675977 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.5094. Min Act: -0.1700
Data Index: 5960902 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4937. Min Act: -0.1700
Data Index: 5922006 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4937. Min Act: -0.1700
Data Index: 385470 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4781. Min Act: -0.1700
Data Index: 6215689 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4937. Min Act: -0.1700
Data Index: 8322326 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4937. Min Act: -0.1700
Data Index: 3277561 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4937. Min Act: -0.1700
Data Index: 7476425 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4624. Min Act: -0.1700
Data Index: 1522686 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7598. Min Range: -3.7598
Max Act: 3.4781. Min Act: -0.1700
Data Index: 7620340 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19