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

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

Neuron 4121 in Layer 1

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: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 493574 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1134183 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0378. Min Act: -0.0002

Data Index: 338517 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0376. Min Act: -0.0002

Data Index: 959904 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1045253 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1089429 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1323912 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0344. Min Act: -0.0002

Data Index: 114393 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0336. Min Act: -0.0002

Data Index: 334146 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0332. Min Act: -0.0002

Data Index: 789306 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0334. Min Act: -0.0002

Data Index: 356073 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1265807 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0322. Min Act: -0.0002

Data Index: 517484 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0315. Min Act: -0.0002

Data Index: 602997 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0308. Min Act: -0.0002

Data Index: 950392 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1185253 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1255928 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0307. Min Act: -0.0002

Data Index: 630665 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1158972 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0303. Min Act: -0.0002

Data Index: 42715 (C4 (Web Text))

Max Activating Token Index: 154