Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2715 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0004

Data Index: 1423649 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0315. Min Act: -0.0004

Data Index: 1136956 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0296. Min Act: -0.0004

Data Index: 1271304 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1219941 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1315049 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0281. Min Act: -0.0004

Data Index: 1383976 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0276. Min Act: -0.0004

Data Index: 1572442 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0241. Min Act: -0.0004

Data Index: 431695 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0275. Min Act: -0.0004

Data Index: 1614095 (Python Code)

Max Activating Token Index: 946

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1367813 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0281. Min Act: -0.0004

Data Index: 1391300 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0262. Min Act: -0.0004

Data Index: 1385501 (Python Code)

Max Activating Token Index: 924

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0284. Min Act: -0.0004

Data Index: 1413738 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0266. Min Act: -0.0004

Data Index: 1000411 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0249. Min Act: -0.0004

Data Index: 1066925 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1377633 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0227. Min Act: -0.0004

Data Index: 186270 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1425286 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0240. Min Act: -0.0004

Data Index: 481770 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1400277 (Python Code)

Max Activating Token Index: 21