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

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

Neuron 947 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0003

Data Index: 897763 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1507. Min Act: -0.0003

Data Index: 667403 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1456. Min Act: -0.0003

Data Index: 106154 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1495. Min Act: -0.0003

Data Index: 651073 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1432. Min Act: -0.0003

Data Index: 254405 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1482. Min Act: -0.0003

Data Index: 1088025 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1356. Min Act: -0.0003

Data Index: 90064 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1298. Min Act: -0.0003

Data Index: 678529 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1290. Min Act: -0.0003

Data Index: 472567 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1383. Min Act: -0.0003

Data Index: 1216378 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1236. Min Act: -0.0003

Data Index: 519615 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1306. Min Act: -0.0003

Data Index: 130934 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1350. Min Act: -0.0003

Data Index: 117798 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1269. Min Act: -0.0003

Data Index: 977020 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1215. Min Act: -0.0003

Data Index: 1290465 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1332. Min Act: -0.0003

Data Index: 1171059 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1218. Min Act: -0.0003

Data Index: 309986 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1247. Min Act: -0.0003

Data Index: 475306 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1292. Min Act: -0.0003

Data Index: 1230287 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1140. Min Act: -0.0003

Data Index: 34613 (C4 (Web Text))

Max Activating Token Index: 494