Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2551 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4331. Min Act: -0.0000

Data Index: 944419 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4315. Min Act: -0.0000

Data Index: 990959 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4319. Min Act: -0.0000

Data Index: 479666 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4305. Min Act: -0.0000

Data Index: 465409 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4301. Min Act: -0.0000

Data Index: 276735 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4308. Min Act: -0.0000

Data Index: 325207 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4287. Min Act: -0.0000

Data Index: 365502 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4223. Min Act: -0.0000

Data Index: 8538 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4211. Min Act: -0.0000

Data Index: 997346 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4206. Min Act: -0.0000

Data Index: 99060 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4203. Min Act: -0.0000

Data Index: 762955 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4212. Min Act: -0.0000

Data Index: 361444 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4210. Min Act: -0.0000

Data Index: 472334 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4204. Min Act: -0.0000

Data Index: 599799 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4213. Min Act: -0.0000

Data Index: 328164 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4202. Min Act: -0.0000

Data Index: 293873 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1358833 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4201. Min Act: -0.0000

Data Index: 780450 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1117002 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1327722 (C4 (Web Text))

Max Activating Token Index: 8