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

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

Neuron 2050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.2261. Min Act: -0.0000

Data Index: 209417 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.2041. Min Act: -0.0000

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1764. Min Act: -0.0000

Data Index: 593930 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1760. Min Act: -0.0000

Data Index: 702286 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1626137 (Python Code)

Max Activating Token Index: 389

Text #5

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1540. Min Act: -0.0000

Data Index: 520136 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1576. Min Act: -0.0000

Data Index: 268833 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1511. Min Act: -0.0000

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1416. Min Act: -0.0000

Data Index: 754287 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1221. Min Act: -0.0000

Data Index: 451223 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1501. Min Act: -0.0000

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1406. Min Act: -0.0000

Data Index: 611349 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1547181 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1525876 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1415. Min Act: -0.0000

Data Index: 878646 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1139. Min Act: -0.0000

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1508826 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1042. Min Act: -0.0000

Data Index: 825456 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1233. Min Act: -0.0000

Data Index: 230594 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.2261. Min Range: -0.2261

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1494486 (Python Code)

Max Activating Token Index: 182