Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.2009. Min Act: -0.1700
Data Index: 3507171 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.1384. Min Act: -0.1700
Data Index: 1047722 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.1384. Min Act: -0.1700
Data Index: 1677318 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.1384. Min Act: -0.1700
Data Index: 3348142 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.0759. Min Act: -0.1700
Data Index: 3467728 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.0759. Min Act: -0.1700
Data Index: 2675982 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.0134. Min Act: -0.1700
Data Index: 1259239 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2009. Min Range: -9.2009
Max Act: 9.0759. Min Act: -0.1700
Data Index: 6359316 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.9509. Min Act: -0.1700
Data Index: 1555501 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.9509. Min Act: -0.1700
Data Index: 4005291 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.9509. Min Act: -0.1700
Data Index: 2355518 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.8884. Min Act: -0.1700
Data Index: 4935211 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.9509. Min Act: -0.1700
Data Index: 5686660 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 3876589 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 5031494 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 1714556 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 12925 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 5686662 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 4798647 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2009. Min Range: -9.2009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 4017331 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19