Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1898 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1263429 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1291670 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1345. Min Act: -0.0002

Data Index: 314349 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1401. Min Act: -0.0002

Data Index: 524222 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1298. Min Act: -0.0002

Data Index: 490810 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1269074 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1357. Min Act: -0.0002

Data Index: 1014020 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1305. Min Act: -0.0002

Data Index: 255932 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1308. Min Act: -0.0002

Data Index: 497753 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1287. Min Act: -0.0002

Data Index: 789598 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1284. Min Act: -0.0002

Data Index: 778691 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1235354 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1220. Min Act: -0.0002

Data Index: 806420 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1329763 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1000185 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1245. Min Act: -0.0002

Data Index: 861566 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1253. Min Act: -0.0002

Data Index: 431913 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1184326 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1243. Min Act: -0.0002

Data Index: 704498 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1152. Min Act: -0.0002

Data Index: 9348 (C4 (Web Text))

Max Activating Token Index: 642