Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1907 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0003

Data Index: 22516 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0328. Min Act: -0.0003

Data Index: 169927 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0311. Min Act: -0.0003

Data Index: 171973 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1107293 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0296. Min Act: -0.0003

Data Index: 524381 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0292. Min Act: -0.0003

Data Index: 811067 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0285. Min Act: -0.0003

Data Index: 130321 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0282. Min Act: -0.0003

Data Index: 712491 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0280. Min Act: -0.0003

Data Index: 461412 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1036105 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1204688 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0273. Min Act: -0.0003

Data Index: 856632 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1025892 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0274. Min Act: -0.0003

Data Index: 373209 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0274. Min Act: -0.0003

Data Index: 528795 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1006899 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0269. Min Act: -0.0003

Data Index: 334761 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1082158 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0267. Min Act: -0.0003

Data Index: 524906 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0266. Min Act: -0.0003

Data Index: 513409 (C4 (Web Text))

Max Activating Token Index: 380