Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0005

Data Index: 1349333 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0278. Min Act: -0.0005

Data Index: 916485 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0286. Min Act: -0.0005

Data Index: 928290 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1349618 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0249. Min Act: -0.0005

Data Index: 368475 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0252. Min Act: -0.0005

Data Index: 15263 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0250. Min Act: -0.0005

Data Index: 251970 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1130472 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0232. Min Act: -0.0005

Data Index: 610443 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0240. Min Act: -0.0005

Data Index: 879048 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1314083 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0233. Min Act: -0.0005

Data Index: 528636 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0252. Min Act: -0.0005

Data Index: 800156 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1218316 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0005

Data Index: 942172 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: -0.0005

Data Index: 926954 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0224. Min Act: -0.0005

Data Index: 1001363 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0226. Min Act: -0.0005

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0201. Min Act: -0.0005

Data Index: 846581 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0005

Data Index: 204427 (C4 (Web Text))

Max Activating Token Index: 920