Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5327 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2643. Min Act: -0.0002

Data Index: 552249 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2476. Min Act: -0.0001

Data Index: 578189 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2421. Min Act: -0.0001

Data Index: 306712 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2358. Min Act: -0.0001

Data Index: 347120 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2377. Min Act: -0.0001

Data Index: 457886 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2309. Min Act: -0.0001

Data Index: 874780 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2265. Min Act: -0.0001

Data Index: 812272 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2258. Min Act: -0.0001

Data Index: 715886 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2257. Min Act: -0.0001

Data Index: 898869 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2220. Min Act: -0.0001

Data Index: 209044 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2237. Min Act: -0.0001

Data Index: 172582 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2260. Min Act: -0.0001

Data Index: 327486 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2214. Min Act: -0.0001

Data Index: 557644 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1331879 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2234. Min Act: -0.0001

Data Index: 320950 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2167. Min Act: -0.0001

Data Index: 503229 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1287547 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1021650 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2210. Min Act: -0.0001

Data Index: 460522 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2174. Min Act: -0.0001

Data Index: 767641 (C4 (Web Text))

Max Activating Token Index: 340