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

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

Neuron 2253 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: 0.1493. Min Range: -0.1493

Max Act: 0.1402. Min Act: -0.0001

Data Index: 277993 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1451. Min Act: -0.0001

Data Index: 983446 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1493. Min Act: -0.0001

Data Index: 484960 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1114154 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1316. Min Act: -0.0002

Data Index: 632508 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1044120 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1135011 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1432. Min Act: -0.0001

Data Index: 614742 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1218509 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1244816 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1196923 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1360. Min Act: -0.0001

Data Index: 686151 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1480. Min Act: -0.0001

Data Index: 504736 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1252. Min Act: -0.0002

Data Index: 1270455 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1340. Min Act: -0.0002

Data Index: 1012001 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1292. Min Act: -0.0001

Data Index: 853194 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1291212 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1296. Min Act: -0.0001

Data Index: 835890 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1230. Min Act: -0.0001

Data Index: 223451 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.1493. Min Range: -0.1493

Max Act: 0.1256. Min Act: -0.0001

Data Index: 760670 (C4 (Web Text))

Max Activating Token Index: 145