Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.7588. Min Act: -0.1700
Data Index: 6452100 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.5401. Min Act: -0.1700
Data Index: 7149543 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.5088. Min Act: -0.1700
Data Index: 736785 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.5713. Min Act: -0.1700
Data Index: 1238979 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.4776. Min Act: -0.1700
Data Index: 7285002 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.5401. Min Act: -0.1700
Data Index: 4101212 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.4776. Min Act: -0.1700
Data Index: 5821490 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.4463. Min Act: -0.1700
Data Index: 708940 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.4151. Min Act: -0.1700
Data Index: 3191102 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.4151. Min Act: -0.1700
Data Index: 1185471 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.3838. Min Act: -0.1700
Data Index: 3914426 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.3838. Min Act: -0.1700
Data Index: 6477058 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.3526. Min Act: -0.1700
Data Index: 8727680 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.3213. Min Act: -0.1700
Data Index: 3260270 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.2901. Min Act: -0.1700
Data Index: 6456589 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.2901. Min Act: -0.1700
Data Index: 5064831 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.2901. Min Act: -0.1700
Data Index: 5613592 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.2901. Min Act: -0.1700
Data Index: 7503578 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.2588. Min Act: -0.1700
Data Index: 4505086 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7588. Min Range: -7.7588
Max Act: 7.1963. Min Act: -0.1700
Data Index: 4449003 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19