Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1529. Min Range: -8.1529
Max Act: 8.1529. Min Act: -0.1700
Data Index: 7389129 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1529. Min Range: -8.1529
Max Act: 8.0279. Min Act: -0.1700
Data Index: 4641712 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.9654. Min Act: -0.1700
Data Index: 341989 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.9654. Min Act: -0.1700
Data Index: 1352468 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.9029. Min Act: -0.1700
Data Index: 5695987 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.8404. Min Act: -0.1700
Data Index: 5215589 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.8404. Min Act: -0.1700
Data Index: 5572917 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.8404. Min Act: -0.1700
Data Index: 1724870 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.8404. Min Act: -0.1700
Data Index: 5077572 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.7779. Min Act: -0.1700
Data Index: 5813430 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.7154. Min Act: -0.1700
Data Index: 5921102 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.7154. Min Act: -0.1700
Data Index: 6284046 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.6529. Min Act: -0.1700
Data Index: 4904089 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.6529. Min Act: -0.1700
Data Index: 6893817 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.6529. Min Act: -0.1700
Data Index: 3608018 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.5904. Min Act: -0.1700
Data Index: 5697885 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.5904. Min Act: -0.1700
Data Index: 3315226 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.5591. Min Act: -0.1700
Data Index: 1929623 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.5591. Min Act: -0.1700
Data Index: 1970963 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1529. Min Range: -8.1529
Max Act: 7.5279. Min Act: -0.1700
Data Index: 2450569 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19