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

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

Neuron 4020 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0001

Data Index: 846881 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1183864 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1492. Min Act: -0.0002

Data Index: 917235 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1456. Min Act: -0.0002

Data Index: 275262 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1453. Min Act: -0.0001

Data Index: 556285 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1437. Min Act: -0.0001

Data Index: 160385 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1444. Min Act: -0.0002

Data Index: 671411 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1324. Min Act: -0.0001

Data Index: 800441 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1345. Min Act: -0.0002

Data Index: 537470 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1369. Min Act: -0.0002

Data Index: 332553 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1361. Min Act: -0.0001

Data Index: 994850 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1339. Min Act: -0.0002

Data Index: 550162 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1288. Min Act: -0.0002

Data Index: 63803 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1253. Min Act: -0.0002

Data Index: 1003744 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1245. Min Act: -0.0002

Data Index: 906121 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1111291 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1302. Min Act: -0.0001

Data Index: 601829 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1233. Min Act: -0.0002

Data Index: 422057 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1236. Min Act: -0.0002

Data Index: 813213 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1234. Min Act: -0.0002

Data Index: 115015 (C4 (Web Text))

Max Activating Token Index: 934