Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3079 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1288182 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.9940. Min Act: -0.0000

Data Index: 436942 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8708. Min Act: -0.0000

Data Index: 298520 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1063843 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1088720 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8650. Min Act: -0.0000

Data Index: 312693 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1116784 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8414. Min Act: -0.0000

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8095. Min Act: -0.0000

Data Index: 484986 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8034. Min Act: -0.0000

Data Index: 721452 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8312. Min Act: -0.0000

Data Index: 196481 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1011918 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7910. Min Act: -0.0000

Data Index: 663502 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.8177. Min Act: -0.0000

Data Index: 420236 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7856. Min Act: -0.0000

Data Index: 239401 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1197520 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7659. Min Act: -0.0000

Data Index: 897938 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7391. Min Act: -0.0000

Data Index: 460288 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1006552 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.9940. Min Range: -0.9940

Max Act: 0.7569. Min Act: -0.0000

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 321