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

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

Neuron 1374 in Layer 2

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: 0.0320. Min Act: -0.0003

Data Index: 1463334 (Python Code)

Max Activating Token Index: 562

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1169144 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1161860 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1331260 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1354526 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0287. Min Act: -0.0003

Data Index: 815171 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0281. Min Act: -0.0003

Data Index: 591003 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0264. Min Act: -0.0003

Data Index: 523592 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0265. Min Act: -0.0003

Data Index: 514161 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1002233 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1630678 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0253. Min Act: -0.0003

Data Index: 249725 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1005536 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0003

Data Index: 515734 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0253. Min Act: -0.0003

Data Index: 458935 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0254. Min Act: -0.0003

Data Index: 466632 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0003

Data Index: 474480 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0003

Data Index: 642186 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0258. Min Act: -0.0003

Data Index: 283900 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0003

Data Index: 795623 (C4 (Web Text))

Max Activating Token Index: 291