Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.9672. Min Act: -0.1700
Data Index: 2959768 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.9672. Min Act: -0.1700
Data Index: 563920 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.7172. Min Act: -0.1700
Data Index: 7968635 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.7172. Min Act: -0.1700
Data Index: 1734017 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.6547. Min Act: -0.1700
Data Index: 6083486 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.6235. Min Act: -0.1700
Data Index: 74837 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.6235. Min Act: -0.1700
Data Index: 1770717 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3633512 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.5297. Min Act: -0.1700
Data Index: 5825454 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4985. Min Act: -0.1700
Data Index: 792973 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4985. Min Act: -0.1700
Data Index: 7792517 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4672. Min Act: -0.1700
Data Index: 4670413 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6755837 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4360. Min Act: -0.1700
Data Index: 285310 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4360. Min Act: -0.1700
Data Index: 3223583 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4047. Min Act: -0.1700
Data Index: 3978840 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4047. Min Act: -0.1700
Data Index: 4108466 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4360. Min Act: -0.1700
Data Index: 4118809 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4047. Min Act: -0.1700
Data Index: 6606897 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9672. Min Range: -5.9672
Max Act: 5.4047. Min Act: -0.1700
Data Index: 7044227 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19