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

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

Neuron 2897 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3530. Min Act: -0.0001

Data Index: 1283946 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2750. Min Act: -0.0001

Data Index: 146660 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2536. Min Act: -0.0001

Data Index: 779176 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2357. Min Act: -0.0001

Data Index: 753275 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2422. Min Act: -0.0001

Data Index: 124391 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2323. Min Act: -0.0001

Data Index: 1136126 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2382. Min Act: -0.0001

Data Index: 846496 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2453. Min Act: -0.0001

Data Index: 716311 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2264. Min Act: -0.0001

Data Index: 980728 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2419. Min Act: -0.0001

Data Index: 832476 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1117171 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1123685 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1208009 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2283. Min Act: -0.0001

Data Index: 1193813 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2198. Min Act: -0.0001

Data Index: 153906 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2162. Min Act: -0.0001

Data Index: 567373 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1355713 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2160. Min Act: -0.0001

Data Index: 503896 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2124. Min Act: -0.0001

Data Index: 961658 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1298432 (C4 (Web Text))

Max Activating Token Index: 931