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

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

Neuron 305 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1262066 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0333. Min Act: -0.0003

Data Index: 534490 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0325. Min Act: -0.0003

Data Index: 389504 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0292. Min Act: -0.0003

Data Index: 204534 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0283. Min Act: -0.0003

Data Index: 310447 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1341754 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0270. Min Act: -0.0003

Data Index: 481742 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0258. Min Act: -0.0004

Data Index: 487497 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0267. Min Act: -0.0003

Data Index: 118351 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0265. Min Act: -0.0003

Data Index: 86392 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0249. Min Act: -0.0003

Data Index: 5306 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1190763 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0257. Min Act: -0.0003

Data Index: 738449 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1188091 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1072421 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1372240 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0269. Min Act: -0.0003

Data Index: 987672 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1375662 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0229. Min Act: -0.0003

Data Index: 304151 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1175638 (C4 (Web Text))

Max Activating Token Index: 501