Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.7676. Min Act: -0.1700
Data Index: 5371741 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.6738. Min Act: -0.1700
Data Index: 4165477 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.5801. Min Act: -0.1700
Data Index: 6923264 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.5488. Min Act: -0.1700
Data Index: 8746618 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.4863. Min Act: -0.1700
Data Index: 4347598 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.4551. Min Act: -0.1700
Data Index: 3226601 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.4238. Min Act: -0.1700
Data Index: 7633970 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.4551. Min Act: -0.1700
Data Index: 1585278 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.3926. Min Act: -0.1700
Data Index: 4166597 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.4238. Min Act: -0.1700
Data Index: 3160835 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.3613. Min Act: -0.1700
Data Index: 5731097 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.3926. Min Act: -0.1700
Data Index: 4926282 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.2988. Min Act: -0.1700
Data Index: 4075928 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.3613. Min Act: -0.1700
Data Index: 4690218 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.3301. Min Act: -0.1700
Data Index: 696177 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.2988. Min Act: -0.1700
Data Index: 356667 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.2988. Min Act: -0.1700
Data Index: 3667020 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.2676. Min Act: -0.1700
Data Index: 2464788 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.2988. Min Act: -0.1700
Data Index: 2668321 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7676. Min Range: -6.7676
Max Act: 6.2363. Min Act: -0.1700
Data Index: 5860254 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19