Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 77 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1267634 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0286. Min Act: -0.0006

Data Index: 366489 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1031190 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0267. Min Act: -0.0006

Data Index: 786880 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0006

Data Index: 679895 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0006

Data Index: 155050 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0263. Min Act: -0.0006

Data Index: 108757 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0006

Data Index: 159065 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0252. Min Act: -0.0006

Data Index: 7548 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0006

Data Index: 736373 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1133541 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0245. Min Act: -0.0005

Data Index: 31811 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0238. Min Act: -0.0006

Data Index: 639717 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0232. Min Act: -0.0006

Data Index: 753081 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0243. Min Act: -0.0006

Data Index: 950495 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1043901 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1296570 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1149038 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0221. Min Act: -0.0006

Data Index: 310644 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0234. Min Act: -0.0006

Data Index: 903422 (C4 (Web Text))

Max Activating Token Index: 457