Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4100 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.6610. Min Act: -0.1700
Data Index: 8124856 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.6610. Min Act: -0.1700
Data Index: 8127184 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5985. Min Act: -0.1700
Data Index: 7556380 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5360. Min Act: -0.1700
Data Index: 8053702 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5360. Min Act: -0.1700
Data Index: 4687012 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5360. Min Act: -0.1700
Data Index: 4628407 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5360. Min Act: -0.1700
Data Index: 6315906 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5048. Min Act: -0.1700
Data Index: 7049642 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5048. Min Act: -0.1700
Data Index: 2519830 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5048. Min Act: -0.1700
Data Index: 5800094 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5048. Min Act: -0.1700
Data Index: 5241306 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.5048. Min Act: -0.1700
Data Index: 7723472 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 3075850 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 4606880 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 5506083 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 6365758 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 1371691 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 7574605 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 6741344 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6610. Min Range: -6.6610
Max Act: 6.4735. Min Act: -0.1700
Data Index: 6755706 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19