Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4412. Min Act: -0.0001

Data Index: 1612111 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4340. Min Act: -0.0001

Data Index: 1621620 (Python Code)

Max Activating Token Index: 904

Text #2

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3649. Min Act: -0.0001

Data Index: 1593872 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1642204 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1626346 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3165. Min Act: -0.0001

Data Index: 1491365 (Python Code)

Max Activating Token Index: 586

Text #6

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3241. Min Act: -0.0001

Data Index: 1447734 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1649904 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3235. Min Act: -0.0001

Data Index: 1492266 (Python Code)

Max Activating Token Index: 784

Text #9

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1383662 (Python Code)

Max Activating Token Index: 724

Text #10

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3001. Min Act: -0.0001

Data Index: 1391368 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1367816 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3193. Min Act: -0.0001

Data Index: 1377226 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3086. Min Act: -0.0001

Data Index: 1549578 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1592952 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3169. Min Act: -0.0001

Data Index: 1392554 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1521232 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1593621 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1631100 (Python Code)

Max Activating Token Index: 659

Text #19

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3253. Min Act: -0.0001

Data Index: 1469470 (Python Code)

Max Activating Token Index: 1015