Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 38 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0006

Data Index: 997311 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0290. Min Act: -0.0006

Data Index: 837481 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0275. Min Act: -0.0006

Data Index: 914931 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0266. Min Act: -0.0006

Data Index: 550629 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0259. Min Act: -0.0006

Data Index: 580928 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0271. Min Act: -0.0006

Data Index: 55635 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0269. Min Act: -0.0005

Data Index: 899273 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0268. Min Act: -0.0006

Data Index: 659221 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0254. Min Act: -0.0006

Data Index: 162545 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1088427 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0246. Min Act: -0.0006

Data Index: 360022 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0258. Min Act: -0.0006

Data Index: 440197 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1253894 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0259. Min Act: -0.0006

Data Index: 151045 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0252. Min Act: -0.0006

Data Index: 418738 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0245. Min Act: -0.0006

Data Index: 494610 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0255. Min Act: -0.0006

Data Index: 888140 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0248. Min Act: -0.0006

Data Index: 124901 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0241. Min Act: -0.0006

Data Index: 254601 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0238. Min Act: -0.0006

Data Index: 265813 (C4 (Web Text))

Max Activating Token Index: 354