Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.5578. Min Act: -0.1700
Data Index: 8268140 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.3390. Min Act: -0.1700
Data Index: 4057396 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.2140. Min Act: -0.1700
Data Index: 5761235 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0578. Min Act: -0.1700
Data Index: 7814429 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0890. Min Act: -0.1700
Data Index: 2677897 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0265. Min Act: -0.1700
Data Index: 3849238 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0578. Min Act: -0.1700
Data Index: 4399015 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5578. Min Range: -7.5578
Max Act: 7.0265. Min Act: -0.1700
Data Index: 7630654 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9640. Min Act: -0.1700
Data Index: 3108647 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9953. Min Act: -0.1700
Data Index: 2346683 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 1750106 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9640. Min Act: -0.1700
Data Index: 1832853 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 4801428 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 5805460 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 6739551 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9015. Min Act: -0.1700
Data Index: 3067676 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 4706947 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 4450523 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9015. Min Act: -0.1700
Data Index: 5489063 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5578. Min Range: -7.5578
Max Act: 6.9015. Min Act: -0.1700
Data Index: 6274696 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19