Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 426 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1878. Min Act: -0.0001

Data Index: 240537 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1093032 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1133392 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1203529 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1415. Min Act: -0.0001

Data Index: 922093 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1455. Min Act: -0.0001

Data Index: 581293 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1383. Min Act: -0.0001

Data Index: 3953 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1441604 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1386. Min Act: -0.0001

Data Index: 978076 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1395. Min Act: -0.0001

Data Index: 669882 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1365. Min Act: -0.0001

Data Index: 764321 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1472087 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1232. Min Act: -0.0000

Data Index: 46932 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1313234 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1397. Min Act: -0.0001

Data Index: 51712 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1063212 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1213. Min Act: -0.0001

Data Index: 909803 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1250. Min Act: -0.0001

Data Index: 697383 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1230. Min Act: -0.0000

Data Index: 666859 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.1878. Min Range: -0.1878

Max Act: 0.1206. Min Act: -0.0000

Data Index: 203021 (C4 (Web Text))

Max Activating Token Index: 655