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

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

Neuron 563 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: 0.0268. Min Range: -0.0268

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1082109 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0253. Min Act: -0.0006

Data Index: 500564 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1327605 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1117173 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1003693 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0239. Min Act: -0.0006

Data Index: 936703 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1071017 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0248. Min Act: -0.0006

Data Index: 614037 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0244. Min Act: -0.0006

Data Index: 196965 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0248. Min Act: -0.0006

Data Index: 833213 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0236. Min Act: -0.0005

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1223154 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0241. Min Act: -0.0006

Data Index: 756141 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0241. Min Act: -0.0005

Data Index: 131706 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0240. Min Act: -0.0006

Data Index: 648465 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0233. Min Act: -0.0006

Data Index: 742317 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0232. Min Act: -0.0006

Data Index: 334222 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0242. Min Act: -0.0006

Data Index: 162539 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0231. Min Act: -0.0006

Data Index: 346070 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0241. Min Act: -0.0006

Data Index: 678261 (C4 (Web Text))

Max Activating Token Index: 28