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

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

Neuron 29 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: 0.1631. Min Range: -0.1631

Max Act: 0.1616. Min Act: -0.0002

Data Index: 1655556 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1631. Min Act: -0.0002

Data Index: 1454070 (Python Code)

Max Activating Token Index: 289

Text #2

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1585. Min Act: -0.0002

Data Index: 1532163 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1612380 (Python Code)

Max Activating Token Index: 318

Text #4

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1438663 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1273. Min Act: -0.0002

Data Index: 9502 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1367557 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1248. Min Act: -0.0002

Data Index: 1426763 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1114276 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1270. Min Act: -0.0002

Data Index: 848363 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1491897 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1379965 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1317. Min Act: -0.0002

Data Index: 1160181 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1043821 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1603473 (Python Code)

Max Activating Token Index: 318

Text #15

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1504993 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1551957 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1201. Min Act: -0.0002

Data Index: 110062 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1303297 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.1631. Min Range: -0.1631

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1427832 (Python Code)

Max Activating Token Index: 150