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

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

Neuron 4168 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.6178. Min Act: -0.0000

Data Index: 563376 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.6365. Min Act: -0.0000

Data Index: 778691 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5456. Min Act: -0.0000

Data Index: 779879 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5455. Min Act: -0.0001

Data Index: 142096 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1325204 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4444. Min Act: -0.0000

Data Index: 409579 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4733. Min Act: -0.0001

Data Index: 185230 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4208. Min Act: -0.0001

Data Index: 1101054 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4738. Min Act: -0.0001

Data Index: 806265 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4379. Min Act: -0.0001

Data Index: 244887 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4362. Min Act: -0.0001

Data Index: 767027 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1158957 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4784. Min Act: -0.0000

Data Index: 525535 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1211688 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4260. Min Act: -0.0001

Data Index: 380950 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4216. Min Act: -0.0000

Data Index: 814169 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1222639 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4330. Min Act: -0.0001

Data Index: 793056 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4429. Min Act: -0.0000

Data Index: 778482 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1174303 (C4 (Web Text))

Max Activating Token Index: 473