Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 72 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0703. Min Range: -2.0703
Max Act: 2.0703. Min Act: -0.0002
Data Index: 476210 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.7688. Min Act: -0.0002
Data Index: 644616 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.8210. Min Act: -0.0001
Data Index: 80787 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.3443. Min Act: -0.0002
Data Index: 197338 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.4459. Min Act: -0.0001
Data Index: 1040812 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.4520. Min Act: -0.0001
Data Index: 1587549 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.5185. Min Act: -0.0002
Data Index: 291788 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.5150. Min Act: -0.0001
Data Index: 1080026 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.3929. Min Act: -0.0002
Data Index: 960332 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.5409. Min Act: -0.0002
Data Index: 156208 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.5624. Min Act: -0.0002
Data Index: 756466 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.3477. Min Act: -0.0002
Data Index: 113470 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.3855. Min Act: -0.0002
Data Index: 1049231 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.4740. Min Act: -0.0001
Data Index: 920654 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.5147. Min Act: -0.0001
Data Index: 133035 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.4505. Min Act: -0.0001
Data Index: 811865 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.3678. Min Act: -0.0002
Data Index: 206711 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.1692. Min Act: -0.0001
Data Index: 161682 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.5179. Min Act: -0.0001
Data Index: 1524694 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0703. Min Range: -2.0703
Max Act: 1.3133. Min Act: -0.0002
Data Index: 202739 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19