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

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

Neuron 5621 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: 2.6980. Min Range: -2.6980

Max Act: 2.6980. Min Act: -0.0000

Data Index: 460091 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.4993. Min Act: -0.0000

Data Index: 1316612 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.4308. Min Act: -0.0000

Data Index: 406335 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.2008. Min Act: -0.0000

Data Index: 1074155 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.0531. Min Act: -0.0000

Data Index: 1251414 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.1321. Min Act: -0.0000

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.1213. Min Act: -0.0000

Data Index: 24985 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.9355. Min Act: -0.0000

Data Index: 808345 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.0070. Min Act: -0.0000

Data Index: 990005 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1124057 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.8606. Min Act: -0.0000

Data Index: 176572 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.9665. Min Act: -0.0000

Data Index: 328673 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.0705. Min Act: -0.0000

Data Index: 1128961 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.9444. Min Act: -0.0000

Data Index: 1090649 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.9388. Min Act: -0.0000

Data Index: 149559 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 2.6980. Min Range: -2.6980

Max Act: 2.0358. Min Act: -0.0000

Data Index: 913923 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.7257. Min Act: -0.0000

Data Index: 377497 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.8128. Min Act: -0.0000

Data Index: 15563 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.8099. Min Act: -0.0000

Data Index: 157843 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 2.6980. Min Range: -2.6980

Max Act: 1.7975. Min Act: -0.0000

Data Index: 180669 (C4 (Web Text))

Max Activating Token Index: 113