Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1280646 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0273. Min Act: -0.0003

Data Index: 542262 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0249. Min Act: -0.0003

Data Index: 589208 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1442273 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0233. Min Act: -0.0003

Data Index: 467119 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0225. Min Act: -0.0003

Data Index: 819150 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0239. Min Act: -0.0003

Data Index: 464054 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0226. Min Act: -0.0003

Data Index: 684330 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1387771 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1045562 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0216. Min Act: -0.0003

Data Index: 611811 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1419773 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1137112 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0216. Min Act: -0.0003

Data Index: 995767 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0212. Min Act: -0.0003

Data Index: 585441 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0217. Min Act: -0.0003

Data Index: 478549 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0217. Min Act: -0.0003

Data Index: 805375 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1495730 (Python Code)

Max Activating Token Index: 448

Text #18

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1356958 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1176062 (C4 (Web Text))

Max Activating Token Index: 777