Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3858 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0806. Min Act: -0.0001
Data Index: 369123 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0659. Min Act: -0.0001
Data Index: 1238127 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0738. Min Act: -0.0001
Data Index: 1078721 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0737. Min Act: -0.0001
Data Index: 362544 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0693. Min Act: -0.0001
Data Index: 1156602 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0725. Min Act: -0.0001
Data Index: 1297923 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0719. Min Act: -0.0001
Data Index: 121627 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0682. Min Act: -0.0001
Data Index: 964688 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0716. Min Act: -0.0001
Data Index: 732143 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0595. Min Act: -0.0001
Data Index: 644635 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0579. Min Act: -0.0001
Data Index: 85574 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0578. Min Act: -0.0001
Data Index: 1575337 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0617. Min Act: -0.0001
Data Index: 446873 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0606. Min Act: -0.0001
Data Index: 748042 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0512. Min Act: -0.0001
Data Index: 291310 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0569. Min Act: -0.0001
Data Index: 744497 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0483. Min Act: -0.0001
Data Index: 138740 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0422. Min Act: -0.0001
Data Index: 687204 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0564. Min Act: -0.0001
Data Index: 643020 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0806. Min Range: -0.0806
Max Act: 0.0494. Min Act: -0.0001
Data Index: 1477438 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19