Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.5871. Min Act: -0.1700
Data Index: 8626050 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3996. Min Act: -0.1700
Data Index: 4236336 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3996. Min Act: -0.1700
Data Index: 4494828 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 3329807 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 1302296 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3371. Min Act: -0.1700
Data Index: 5685665 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3059. Min Act: -0.1700
Data Index: 3363434 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.3059. Min Act: -0.1700
Data Index: 1941244 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2746. Min Act: -0.1700
Data Index: 3414357 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 3412725 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 7652237 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 4847681 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 5915790 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 360738 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 266418 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2434. Min Act: -0.1700
Data Index: 2324901 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2121. Min Act: -0.1700
Data Index: 4740272 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.1809. Min Act: -0.1700
Data Index: 7565617 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.2121. Min Act: -0.1700
Data Index: 5645441 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5871. Min Range: -4.5871
Max Act: 4.1809. Min Act: -0.1700
Data Index: 1446324 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19