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

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

Neuron 4219 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.4420. Min Act: -0.0000

Data Index: 480397 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.4526. Min Act: -0.0000

Data Index: 214555 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.2774. Min Act: -0.0000

Data Index: 608873 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.3348. Min Act: -0.0000

Data Index: 681334 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.2218. Min Act: -0.0000

Data Index: 241445 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.2040. Min Act: -0.0000

Data Index: 1053075 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.0525. Min Act: -0.0000

Data Index: 985016 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.1359. Min Act: -0.0000

Data Index: 122955 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.2677. Min Act: -0.0000

Data Index: 1025745 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.1368. Min Act: -0.0000

Data Index: 1225731 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.0767. Min Act: -0.0000

Data Index: 1147219 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.0645. Min Act: -0.0000

Data Index: 1062440 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.4526. Min Range: -2.4526

Max Act: 1.9325. Min Act: -0.0000

Data Index: 1261303 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 2.4526. Min Range: -2.4526

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 2.4526. Min Range: -2.4526

Max Act: 1.8727. Min Act: -0.0000

Data Index: 1241879 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 2.4526. Min Range: -2.4526

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1071208 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 2.4526. Min Range: -2.4526

Max Act: 1.9190. Min Act: -0.0000

Data Index: 468654 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1346097 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 2.4526. Min Range: -2.4526

Max Act: 2.0001. Min Act: -0.0000

Data Index: 1297131 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.4526. Min Range: -2.4526

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1301015 (C4 (Web Text))

Max Activating Token Index: 297