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

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

Neuron 2227 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: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1060927 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1509. Min Act: -0.0001

Data Index: 21267 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1344. Min Act: -0.0001

Data Index: 884380 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1271. Min Act: -0.0001

Data Index: 591684 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1090781 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1363. Min Act: -0.0001

Data Index: 10659 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1208. Min Act: -0.0001

Data Index: 126620 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1241. Min Act: -0.0001

Data Index: 542456 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1345622 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1251332 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1265. Min Act: -0.0001

Data Index: 820969 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1184. Min Act: -0.0001

Data Index: 717062 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1011331 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1114. Min Act: -0.0001

Data Index: 972218 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1165. Min Act: -0.0001

Data Index: 450378 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1184. Min Act: -0.0001

Data Index: 267066 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1171. Min Act: -0.0001

Data Index: 559844 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1200. Min Act: -0.0001

Data Index: 697191 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1605057 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1166. Min Act: -0.0001

Data Index: 66298 (C4 (Web Text))

Max Activating Token Index: 526