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

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

Neuron 696 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: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0004

Data Index: 228889 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0377. Min Act: -0.0004

Data Index: 1083366 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0351. Min Act: -0.0004

Data Index: 707915 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0359. Min Act: -0.0004

Data Index: 639112 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0347. Min Act: -0.0004

Data Index: 912947 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0339. Min Act: -0.0004

Data Index: 28602 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1130860 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0335. Min Act: -0.0004

Data Index: 1350053 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1172466 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0304. Min Act: -0.0004

Data Index: 781181 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0313. Min Act: -0.0004

Data Index: 314390 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1280360 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0340. Min Act: -0.0004

Data Index: 24492 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0325. Min Act: -0.0004

Data Index: 296086 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0305. Min Act: -0.0004

Data Index: 113454 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0307. Min Act: -0.0004

Data Index: 829835 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0312. Min Act: -0.0004

Data Index: 142516 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0305. Min Act: -0.0004

Data Index: 15397 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0295. Min Act: -0.0004

Data Index: 701916 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0298. Min Act: -0.0004

Data Index: 1197094 (C4 (Web Text))

Max Activating Token Index: 881