Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1963 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0003

Data Index: 291778 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0266. Min Act: -0.0004

Data Index: 278638 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0260. Min Act: -0.0003

Data Index: 421452 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0246. Min Act: -0.0003

Data Index: 728027 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0254. Min Act: -0.0003

Data Index: 383154 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0249. Min Act: -0.0004

Data Index: 115463 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1293924 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0236. Min Act: -0.0003

Data Index: 521952 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0229. Min Act: -0.0003

Data Index: 957212 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0227. Min Act: -0.0003

Data Index: 192105 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1589474 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0222. Min Act: -0.0003

Data Index: 263428 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1141206 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0221. Min Act: -0.0003

Data Index: 600478 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1273493 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1559573 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0215. Min Act: -0.0003

Data Index: 461484 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0219. Min Act: -0.0003

Data Index: 701518 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1191756 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0219. Min Act: -0.0003

Data Index: 886643 (C4 (Web Text))

Max Activating Token Index: 325