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

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

Neuron 1612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.4475. Min Act: -0.0000

Data Index: 636992 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1599134 (Python Code)

Max Activating Token Index: 723

Text #2

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1465279 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1926. Min Act: -0.0000

Data Index: 8793 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1574598 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1512518 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2374. Min Act: -0.0000

Data Index: 1308664 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1180212 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1397. Min Act: -0.0000

Data Index: 360150 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2072. Min Act: -0.0000

Data Index: 580479 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1943. Min Act: -0.0000

Data Index: 676266 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1024. Min Act: -0.0000

Data Index: 227615 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1345187 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1535124 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1476629 (Python Code)

Max Activating Token Index: 548

Text #15

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1600147 (Python Code)

Max Activating Token Index: 997

Text #16

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1467995 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1351029 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1420317 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1148582 (C4 (Web Text))

Max Activating Token Index: 332