Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 332 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0352. Min Act: -0.0004

Data Index: 1613044 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0379. Min Act: -0.0003

Data Index: 811221 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0398. Min Act: -0.0003

Data Index: 932346 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0322. Min Act: -0.0003

Data Index: 799007 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0365. Min Act: -0.0003

Data Index: 77908 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1351768 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0333. Min Act: -0.0003

Data Index: 459638 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0276. Min Act: -0.0003

Data Index: 662100 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0310. Min Act: -0.0003

Data Index: 924275 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1526248 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0271. Min Act: -0.0004

Data Index: 61083 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1349174 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1324234 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1418207 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1607680 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0273. Min Act: -0.0003

Data Index: 482318 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1640899 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1009064 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1048697 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1091578 (C4 (Web Text))

Max Activating Token Index: 1004