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

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

Neuron 3553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1449681 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1485723 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0396. Min Act: -0.0001

Data Index: 1389418 (Python Code)

Max Activating Token Index: 313

Text #3

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1456905 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0141. Min Act: -0.0001

Data Index: 1530443 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9586. Min Act: -0.0001

Data Index: 1397665 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1382984 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1592031 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9433. Min Act: -0.0001

Data Index: 1622377 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1577794 (Python Code)

Max Activating Token Index: 843

Text #10

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8672. Min Act: -0.0001

Data Index: 1605324 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1428942 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1361027 (Python Code)

Max Activating Token Index: 930

Text #13

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1401151 (Python Code)

Max Activating Token Index: 782

Text #14

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8240. Min Act: -0.0001

Data Index: 1520796 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8372. Min Act: -0.0001

Data Index: 1574841 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8049. Min Act: -0.0001

Data Index: 1530251 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1476090 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8456. Min Act: -0.0001

Data Index: 1383991 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1492537 (Python Code)

Max Activating Token Index: 442