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

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

Neuron 2190 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0372. Min Act: -0.0001

Data Index: 924538 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1299462 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0327. Min Act: -0.0001

Data Index: 2841 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0297. Min Act: -0.0001

Data Index: 851532 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1066766 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0294. Min Act: -0.0001

Data Index: 350616 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0290. Min Act: -0.0001

Data Index: 106976 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0273. Min Act: -0.0001

Data Index: 139977 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1202200 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1149265 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0275. Min Act: -0.0001

Data Index: 285490 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1218418 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0267. Min Act: -0.0001

Data Index: 524711 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0278. Min Act: -0.0001

Data Index: 836912 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0275. Min Act: -0.0001

Data Index: 675238 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1081943 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0265. Min Act: -0.0001

Data Index: 245199 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0255. Min Act: -0.0001

Data Index: 343970 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0244. Min Act: -0.0001

Data Index: 246943 (C4 (Web Text))

Max Activating Token Index: 818