Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1520 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0006

Data Index: 547555 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0389. Min Act: -0.0006

Data Index: 448768 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1049721 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0366. Min Act: -0.0006

Data Index: 1150078 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0357. Min Act: -0.0006

Data Index: 141497 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0386. Min Act: -0.0006

Data Index: 874622 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0368. Min Act: -0.0006

Data Index: 668184 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0366. Min Act: -0.0006

Data Index: 587893 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0372. Min Act: -0.0006

Data Index: 563862 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0367. Min Act: -0.0006

Data Index: 949021 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0331. Min Act: -0.0006

Data Index: 301603 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0322. Min Act: -0.0006

Data Index: 78164 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0341. Min Act: -0.0006

Data Index: 207161 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0344. Min Act: -0.0006

Data Index: 1165744 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0344. Min Act: -0.0006

Data Index: 122629 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0329. Min Act: -0.0006

Data Index: 779243 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1358754 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0319. Min Act: -0.0006

Data Index: 186058 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0345. Min Act: -0.0006

Data Index: 1191395 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0335. Min Act: -0.0006

Data Index: 122403 (C4 (Web Text))

Max Activating Token Index: 209