Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4828 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.2041. Min Act: -0.0000

Data Index: 385781 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1150587 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1885. Min Act: -0.0000

Data Index: 552957 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1865. Min Act: -0.0000

Data Index: 484333 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1698. Min Act: -0.0000

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1560. Min Act: -0.0000

Data Index: 397439 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1009216 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1030162 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1484. Min Act: -0.0000

Data Index: 62724 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1451. Min Act: -0.0000

Data Index: 317745 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1264375 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1365. Min Act: -0.0000

Data Index: 873549 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1359. Min Act: -0.0000

Data Index: 644858 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1341. Min Act: -0.0000

Data Index: 511837 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1368. Min Act: -0.0000

Data Index: 591173 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1224. Min Act: -0.0000

Data Index: 788605 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1152402 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1197. Min Act: -0.0000

Data Index: 676498 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1206. Min Act: -0.0000

Data Index: 446495 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.2041. Min Range: -0.2041

Max Act: 0.1133. Min Act: -0.0000

Data Index: 209318 (C4 (Web Text))

Max Activating Token Index: 329