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

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

Neuron 1360 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.4931. Min Act: -0.0002

Data Index: 1558919 (Python Code)

Max Activating Token Index: 595

Text #1

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2604. Min Act: -0.0002

Data Index: 1535810 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2760. Min Act: -0.0002

Data Index: 1511111 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2453. Min Act: -0.0002

Data Index: 1476399 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1821. Min Act: -0.0002

Data Index: 1578210 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2050. Min Act: -0.0002

Data Index: 1471738 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1612. Min Act: -0.0002

Data Index: 1603936 (Python Code)

Max Activating Token Index: 929

Text #7

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.0330. Min Act: -0.0002

Data Index: 1450943 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1297. Min Act: -0.0002

Data Index: 1468025 (Python Code)

Max Activating Token Index: 535

Text #9

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.0693. Min Act: -0.0002

Data Index: 1590872 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1328. Min Act: -0.0002

Data Index: 1636283 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1146. Min Act: -0.0002

Data Index: 1400834 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1742. Min Act: -0.0002

Data Index: 1603631 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2038. Min Act: -0.0002

Data Index: 1533325 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1264. Min Act: -0.0002

Data Index: 1619407 (Python Code)

Max Activating Token Index: 653

Text #15

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.0176. Min Act: -0.0002

Data Index: 1445516 (Python Code)

Max Activating Token Index: 592

Text #16

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.0626. Min Act: -0.0002

Data Index: 1438796 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.0163. Min Act: -0.0002

Data Index: 1482050 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.0358. Min Act: -0.0002

Data Index: 1415853 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 1.4931. Min Range: -1.4931

Max Act: 0.9992. Min Act: -0.0002

Data Index: 1432624 (Python Code)

Max Activating Token Index: 171