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

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

Neuron 4549 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0000

Data Index: 642617 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1693. Min Act: -0.0000

Data Index: 560194 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1582. Min Act: -0.0000

Data Index: 975468 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1564. Min Act: -0.0000

Data Index: 422438 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1480. Min Act: -0.0000

Data Index: 787895 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1159512 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1442. Min Act: -0.0000

Data Index: 531659 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1310517 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1288. Min Act: -0.0000

Data Index: 495680 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1243. Min Act: -0.0000

Data Index: 813906 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1287. Min Act: -0.0000

Data Index: 884499 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1237726 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1266. Min Act: -0.0000

Data Index: 954964 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1221. Min Act: -0.0000

Data Index: 940187 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1194. Min Act: -0.0000

Data Index: 382771 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1273. Min Act: -0.0000

Data Index: 379206 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1221. Min Act: -0.0000

Data Index: 798909 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1175. Min Act: -0.0000

Data Index: 357469 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1235716 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1206. Min Act: -0.0000

Data Index: 361327 (C4 (Web Text))

Max Activating Token Index: 436