Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8910. Min Act: -0.0722
Data Index: 2270891 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.8910. Min Act: 0.0673
Data Index: 6228900 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7797. Min Act: -0.0806
Data Index: 5107893 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7558. Min Act: -0.0664
Data Index: 638378 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7399. Min Act: -0.0164
Data Index: 3484299 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7319. Min Act: -0.1348
Data Index: 5033093 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7239. Min Act: -0.1225
Data Index: 5880580 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7079. Min Act: -0.1348
Data Index: 699335 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.7079. Min Act: -0.0557
Data Index: 2936129 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6759. Min Act: 0.2908
Data Index: 4238626 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6839. Min Act: -0.1165
Data Index: 4445968 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6679. Min Act: -0.1185
Data Index: 6823727 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6839. Min Act: -0.1465
Data Index: 7174073 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6759. Min Act: -0.0912
Data Index: 7778705 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6839. Min Act: -0.0779
Data Index: 7689326 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6919. Min Act: -0.1244
Data Index: 5573625 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6518. Min Act: -0.0987
Data Index: 1947536 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6679. Min Act: -0.1490
Data Index: 912434 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6598. Min Act: -0.1380
Data Index: 1280196 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8910. Min Range: -2.8910
Max Act: 2.6679. Min Act: -0.0541
Data Index: 7585245 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19