Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3833 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.1439. Min Act: -0.0001
Data Index: 595060 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.4507. Min Act: -0.0001
Data Index: 633584 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.2827. Min Act: -0.0000
Data Index: 696574 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.4910. Min Act: -0.0000
Data Index: 566005 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.2430. Min Act: -0.0000
Data Index: 108126 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.1201. Min Act: -0.0001
Data Index: 1269770 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.4763. Min Act: -0.0001
Data Index: 973233 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.2857. Min Act: -0.0000
Data Index: 658717 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.5373. Min Act: -0.0000
Data Index: 905341 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5373. Min Range: -2.5373
Max Act: 1.9614. Min Act: -0.0001
Data Index: 566055 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.2815. Min Act: -0.0001
Data Index: 901691 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5373. Min Range: -2.5373
Max Act: 1.8277. Min Act: -0.0001
Data Index: 447382 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.0635. Min Act: -0.0000
Data Index: 29892 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.0571. Min Act: -0.0001
Data Index: 302738 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5373. Min Range: -2.5373
Max Act: 1.9494. Min Act: -0.0001
Data Index: 998029 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.0342. Min Act: -0.0001
Data Index: 849314 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5373. Min Range: -2.5373
Max Act: 1.9327. Min Act: -0.0001
Data Index: 902607 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.0223. Min Act: -0.0000
Data Index: 1192195 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.0368. Min Act: -0.0000
Data Index: 17030 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5373. Min Range: -2.5373
Max Act: 2.0192. Min Act: -0.0001
Data Index: 1084842 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19