Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0201. Min Range: -1.0201

Max Act: 1.0201. Min Act: -0.0000

Data Index: 52150 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9844. Min Act: -0.0000

Data Index: 720292 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9790. Min Act: -0.0000

Data Index: 326098 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9285. Min Act: -0.0001

Data Index: 551227 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1085738 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8987. Min Act: -0.0000

Data Index: 934268 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1042352 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1007048 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8242. Min Act: -0.0001

Data Index: 186309 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7904. Min Act: -0.0000

Data Index: 857186 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8232. Min Act: -0.0000

Data Index: 309404 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8350. Min Act: -0.0000

Data Index: 681448 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7835. Min Act: -0.0000

Data Index: 258996 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8142. Min Act: -0.0001

Data Index: 295268 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7146. Min Act: -0.0000

Data Index: 852684 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7580. Min Act: -0.0000

Data Index: 98551 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6361. Min Act: -0.0000

Data Index: 50203 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1255207 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7102. Min Act: -0.0000

Data Index: 475517 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1016814 (C4 (Web Text))

Max Activating Token Index: 14