Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.7378. Min Act: -0.1700
Data Index: 8602312 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.4878. Min Act: -0.1700
Data Index: 5479319 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.4253. Min Act: -0.1700
Data Index: 3940132 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.3941. Min Act: -0.1700
Data Index: 5467544 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.3628. Min Act: -0.1700
Data Index: 7594644 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.3316. Min Act: -0.1700
Data Index: 2684850 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.2691. Min Act: -0.1700
Data Index: 8043246 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.0816. Min Act: -0.1700
Data Index: 6073733 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2730295 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.0503. Min Act: -0.1700
Data Index: 8747672 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.0191. Min Act: -0.1700
Data Index: 2346868 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7378. Min Range: -5.7378
Max Act: 5.0191. Min Act: -0.1700
Data Index: 932439 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5515200 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9878. Min Act: -0.1700
Data Index: 7549667 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9566. Min Act: -0.1700
Data Index: 7829774 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9566. Min Act: -0.1700
Data Index: 7849853 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9566. Min Act: -0.1700
Data Index: 8352468 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9566. Min Act: -0.1700
Data Index: 6522483 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9253. Min Act: -0.1700
Data Index: 5936751 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7378. Min Range: -5.7378
Max Act: 4.9566. Min Act: -0.1700
Data Index: 6037957 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19