Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4675. Min Act: -0.0002

Data Index: 1336652 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4610. Min Act: -0.0002

Data Index: 833495 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4404. Min Act: -0.0002

Data Index: 659268 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4406. Min Act: -0.0002

Data Index: 430361 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4270. Min Act: -0.0002

Data Index: 1142390 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4314. Min Act: -0.0002

Data Index: 727877 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4301. Min Act: -0.0002

Data Index: 1135186 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4241. Min Act: -0.0002

Data Index: 668746 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4188. Min Act: -0.0002

Data Index: 54757 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4250. Min Act: -0.0002

Data Index: 390751 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4136. Min Act: -0.0002

Data Index: 220167 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4162. Min Act: -0.0002

Data Index: 599695 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4221. Min Act: -0.0002

Data Index: 870441 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4263. Min Act: -0.0002

Data Index: 375099 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4198. Min Act: -0.0002

Data Index: 659232 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4125. Min Act: -0.0002

Data Index: 347233 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4222. Min Act: -0.0002

Data Index: 827662 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4204. Min Act: -0.0002

Data Index: 1262113 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4149. Min Act: -0.0002

Data Index: 402664 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.4675. Min Range: -0.4675

Max Act: 0.4200. Min Act: -0.0002

Data Index: 748549 (C4 (Web Text))

Max Activating Token Index: 836