Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0001

Data Index: 450288 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1448. Min Act: -0.0001

Data Index: 667560 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1388. Min Act: -0.0001

Data Index: 497958 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1333. Min Act: -0.0001

Data Index: 587570 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1365. Min Act: -0.0001

Data Index: 595220 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1378. Min Act: -0.0000

Data Index: 769811 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1215557 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1338. Min Act: -0.0001

Data Index: 637657 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1261. Min Act: -0.0001

Data Index: 151192 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1257. Min Act: -0.0001

Data Index: 533977 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1264. Min Act: -0.0001

Data Index: 357016 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1256. Min Act: -0.0001

Data Index: 848359 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1293. Min Act: -0.0001

Data Index: 382287 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1289. Min Act: -0.0001

Data Index: 960889 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1276. Min Act: -0.0001

Data Index: 782150 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1180. Min Act: -0.0000

Data Index: 978223 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1188. Min Act: -0.0001

Data Index: 482043 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1211. Min Act: -0.0001

Data Index: 927682 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1216. Min Act: -0.0001

Data Index: 343523 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1188653 (C4 (Web Text))

Max Activating Token Index: 881