Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 141 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0001

Data Index: 729778 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0300. Min Act: -0.0001

Data Index: 810364 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0323. Min Act: -0.0001

Data Index: 313641 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1244 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0292. Min Act: -0.0001

Data Index: 434485 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0303. Min Act: -0.0001

Data Index: 171818 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0290. Min Act: -0.0001

Data Index: 285625 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0297. Min Act: -0.0001

Data Index: 686021 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1079577 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1425623 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0281. Min Act: -0.0001

Data Index: 111680 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0284. Min Act: -0.0001

Data Index: 298197 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0269. Min Act: -0.0001

Data Index: 450091 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1289768 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0264. Min Act: -0.0001

Data Index: 719836 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0244. Min Act: -0.0001

Data Index: 986594 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1041548 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0001

Data Index: 245017 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0266. Min Act: -0.0001

Data Index: 472046 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0275. Min Act: -0.0001

Data Index: 306776 (C4 (Web Text))

Max Activating Token Index: 756