Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2025 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.4091. Min Act: -0.0001
Data Index: 171729 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.4497. Min Act: -0.0001
Data Index: 991075 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.4289. Min Act: -0.0001
Data Index: 1308457 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.4056. Min Act: -0.0001
Data Index: 1091804 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3381. Min Act: -0.0001
Data Index: 628426 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3720. Min Act: -0.0001
Data Index: 309805 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3621. Min Act: -0.0001
Data Index: 231498 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3664. Min Act: -0.0001
Data Index: 668714 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3767. Min Act: -0.0001
Data Index: 1196019 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3756. Min Act: -0.0001
Data Index: 75144 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3403. Min Act: -0.0001
Data Index: 206993 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3577. Min Act: -0.0001
Data Index: 1200135 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3555. Min Act: -0.0001
Data Index: 15555 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3553. Min Act: -0.0001
Data Index: 1300848 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3561. Min Act: -0.0001
Data Index: 82770 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3528. Min Act: -0.0001
Data Index: 1212298 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3475. Min Act: -0.0001
Data Index: 15644 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3401. Min Act: -0.0001
Data Index: 1146198 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3495. Min Act: -0.0001
Data Index: 732655 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4497. Min Range: -0.4497
Max Act: 0.3489. Min Act: -0.0001
Data Index: 251356 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19