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

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

Neuron 3583 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6432. Min Act: -0.0000

Data Index: 15226 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1293590 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5600. Min Act: -0.0001

Data Index: 1533824 (Python Code)

Max Activating Token Index: 885

Text #3

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6606. Min Act: -0.0001

Data Index: 1408645 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6346. Min Act: -0.0001

Data Index: 1543835 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5415. Min Act: -0.0001

Data Index: 1513720 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5960. Min Act: -0.0001

Data Index: 1515019 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5586. Min Act: -0.0000

Data Index: 169816 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5111. Min Act: -0.0001

Data Index: 1377299 (Python Code)

Max Activating Token Index: 855

Text #9

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.6094. Min Act: -0.0001

Data Index: 1485561 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5888. Min Act: -0.0001

Data Index: 1408967 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5336. Min Act: -0.0000

Data Index: 69714 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5917. Min Act: -0.0001

Data Index: 1401911 (Python Code)

Max Activating Token Index: 952

Text #13

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5188. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1387486 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5240. Min Act: -0.0001

Data Index: 1516949 (Python Code)

Max Activating Token Index: 282

Text #16

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1136983 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1499229 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.4999. Min Act: -0.0001

Data Index: 1645556 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 0.6606. Min Range: -0.6606

Max Act: 0.5118. Min Act: -0.0000

Data Index: 575466 (C4 (Web Text))

Max Activating Token Index: 392