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

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

Neuron 3620 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0361. Min Act: -0.0002

Data Index: 737020 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0340. Min Act: -0.0002

Data Index: 867866 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0313. Min Act: -0.0002

Data Index: 973335 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0304. Min Act: -0.0002

Data Index: 167670 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0300. Min Act: -0.0002

Data Index: 163037 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0317. Min Act: -0.0002

Data Index: 648261 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0288. Min Act: -0.0002

Data Index: 550112 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0308. Min Act: -0.0002

Data Index: 303128 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0291. Min Act: -0.0002

Data Index: 646227 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0286. Min Act: -0.0002

Data Index: 467876 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1589100 (Python Code)

Max Activating Token Index: 870

Text #12

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1138227 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1500150 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1656928 (Python Code)

Max Activating Token Index: 513

Text #15

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1200651 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0280. Min Act: -0.0002

Data Index: 971014 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0278. Min Act: -0.0002

Data Index: 762077 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1181632 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0273. Min Act: -0.0002

Data Index: 162892 (C4 (Web Text))

Max Activating Token Index: 343