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

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

Neuron 2825 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: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0003

Data Index: 534409 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0300. Min Act: -0.0003

Data Index: 893801 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1656680 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1164958 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1466270 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1235628 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1001727 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1256703 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1645770 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1415750 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0260. Min Act: -0.0004

Data Index: 602649 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0281. Min Act: -0.0003

Data Index: 554528 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1437771 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0254. Min Act: -0.0003

Data Index: 831075 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0252. Min Act: -0.0003

Data Index: 219608 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0241. Min Act: -0.0003

Data Index: 534243 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1004408 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0252. Min Act: -0.0003

Data Index: 278843 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0223. Min Act: -0.0003

Data Index: 994911 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0232. Min Act: -0.0003

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 115