Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.6458. Min Act: -0.0000

Data Index: 251051 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.5748. Min Act: -0.0000

Data Index: 167771 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.4661. Min Act: -0.0000

Data Index: 288740 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.4157. Min Act: -0.0000

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1147501 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.4714. Min Act: -0.0000

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.3019. Min Act: -0.0000

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.2572. Min Act: -0.0000

Data Index: 1358433 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.1113. Min Act: -0.0000

Data Index: 589100 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.4768. Min Act: -0.0000

Data Index: 869334 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.1204. Min Act: -0.0000

Data Index: 1293185 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 2.6458. Min Range: -2.6458

Max Act: 1.8708. Min Act: -0.0000

Data Index: 292837 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.6458. Min Range: -2.6458

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1265586 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 2.6458. Min Range: -2.6458

Max Act: 1.9447. Min Act: -0.0000

Data Index: 280914 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.0369. Min Act: -0.0000

Data Index: 58257 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1217503 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.0237. Min Act: -0.0000

Data Index: 1136786 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.0212. Min Act: -0.0000

Data Index: 671984 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1093324 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 2.6458. Min Range: -2.6458

Max Act: 2.0094. Min Act: -0.0000

Data Index: 1313207 (C4 (Web Text))

Max Activating Token Index: 424