Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3154 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0003

Data Index: 81582 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1514. Min Act: -0.0003

Data Index: 502578 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1456. Min Act: -0.0003

Data Index: 954545 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1389. Min Act: -0.0002

Data Index: 164670 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1338. Min Act: -0.0003

Data Index: 1029743 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1282. Min Act: -0.0003

Data Index: 946716 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1375. Min Act: -0.0003

Data Index: 60343 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1321. Min Act: -0.0003

Data Index: 69777 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1359. Min Act: -0.0003

Data Index: 253648 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1295. Min Act: -0.0002

Data Index: 565548 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1326. Min Act: -0.0003

Data Index: 472321 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1288. Min Act: -0.0002

Data Index: 514313 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1274. Min Act: -0.0003

Data Index: 435672 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1212. Min Act: -0.0002

Data Index: 493086 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1210. Min Act: -0.0003

Data Index: 286068 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1290. Min Act: -0.0003

Data Index: 1223584 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1244. Min Act: -0.0002

Data Index: 635169 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1188. Min Act: -0.0003

Data Index: 174444 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1225. Min Act: -0.0003

Data Index: 1040445 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1213. Min Act: -0.0003

Data Index: 1193830 (C4 (Web Text))

Max Activating Token Index: 431