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

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

Neuron 3159 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1424. Min Act: -0.0002

Data Index: 158292 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0002

Data Index: 975058 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1160. Min Act: -0.0002

Data Index: 923936 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1427. Min Act: -0.0002

Data Index: 581000 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1111507 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1438. Min Act: -0.0002

Data Index: 472560 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1379. Min Act: -0.0002

Data Index: 135063 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1430. Min Act: -0.0002

Data Index: 746134 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1364. Min Act: -0.0002

Data Index: 141718 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1436. Min Act: -0.0002

Data Index: 147543 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1325. Min Act: -0.0002

Data Index: 691516 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1025075 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1308. Min Act: -0.0002

Data Index: 960202 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1321. Min Act: -0.0002

Data Index: 654897 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1303797 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1300. Min Act: -0.0002

Data Index: 644412 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1382. Min Act: -0.0002

Data Index: 46471 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1259. Min Act: -0.0002

Data Index: 145192 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1259. Min Act: -0.0002

Data Index: 675583 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1251. Min Act: -0.0002

Data Index: 776426 (C4 (Web Text))

Max Activating Token Index: 364