Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5319 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1932. Min Act: -0.0000

Data Index: 812726 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1209867 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1564. Min Act: -0.0000

Data Index: 409945 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1542. Min Act: -0.0000

Data Index: 970392 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1521. Min Act: -0.0000

Data Index: 477269 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1341893 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1000593 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1476. Min Act: -0.0000

Data Index: 84046 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1480. Min Act: -0.0000

Data Index: 983718 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1434. Min Act: -0.0000

Data Index: 862742 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1424. Min Act: -0.0000

Data Index: 803934 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1436. Min Act: -0.0000

Data Index: 135239 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1291. Min Act: -0.0000

Data Index: 976044 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1023270 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1140858 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1300. Min Act: -0.0000

Data Index: 779530 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1378. Min Act: -0.0000

Data Index: 857036 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1296. Min Act: -0.0000

Data Index: 853361 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1270. Min Act: -0.0000

Data Index: 487729 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1268. Min Act: -0.0000

Data Index: 490886 (C4 (Web Text))

Max Activating Token Index: 943