Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0488. Min Range: -9.0488
Max Act: 9.0488. Min Act: -0.1700
Data Index: 8181764 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.9863. Min Act: -0.1700
Data Index: 4901241 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.9863. Min Act: -0.1700
Data Index: 5544076 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.9238. Min Act: -0.1700
Data Index: 3053756 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.8613. Min Act: -0.1700
Data Index: 7595997 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.8613. Min Act: -0.1700
Data Index: 6183748 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.8613. Min Act: -0.1700
Data Index: 3416087 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.9238. Min Act: -0.1700
Data Index: 4867626 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.8613. Min Act: -0.1700
Data Index: 8070149 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.8613. Min Act: -0.1700
Data Index: 1245444 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7988. Min Act: -0.1700
Data Index: 7492368 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7988. Min Act: -0.1700
Data Index: 4536680 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 3881447 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 8079665 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 6838969 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 3602439 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 4137441 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 5305677 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.7363. Min Act: -0.1700
Data Index: 6572583 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0488. Min Range: -9.0488
Max Act: 8.6738. Min Act: -0.1700
Data Index: 5835266 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19