Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3590 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1526. Min Act: -0.0000

Data Index: 692404 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1507. Min Act: 0.0000

Data Index: 186651 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1468. Min Act: 0.0000

Data Index: 596081 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1406. Min Act: 0.0000

Data Index: 417399 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1403. Min Act: 0.0000

Data Index: 131046 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1395. Min Act: -0.0000

Data Index: 985755 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1381. Min Act: 0.0000

Data Index: 271306 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1373. Min Act: 0.0000

Data Index: 373403 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1370. Min Act: 0.0000

Data Index: 765507 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1306. Min Act: -0.0000

Data Index: 468096 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1345. Min Act: 0.0000

Data Index: 683491 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1342. Min Act: 0.0000

Data Index: 2103 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1344. Min Act: 0.0000

Data Index: 915085 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1339. Min Act: 0.0000

Data Index: 1586076 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1337. Min Act: 0.0000

Data Index: 1376664 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1335. Min Act: 0.0000

Data Index: 1811022 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1252880 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1279. Min Act: 0.0000

Data Index: 197898 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1317. Min Act: -0.0000

Data Index: 903437 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1365. Min Act: 0.0000

Data Index: 498242 (The Pile)

Max Activating Token Index: 1023