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

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

Neuron 3012 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.8294. Min Act: -0.0000

Data Index: 1614075 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1511933 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1555375 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1369677 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1484316 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1570228 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.2154. Min Act: -0.0000

Data Index: 746854 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1589675 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1650459 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1086055 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.9466. Min Act: -0.0000

Data Index: 718114 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.8294. Min Range: -1.8294

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1457875 (Python Code)

Max Activating Token Index: 433

Text #12

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1640163 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1431557 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1567826 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1049810 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1572569 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1652187 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.7065. Min Act: -0.0000

Data Index: 577209 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.8294. Min Range: -1.8294

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1387222 (Python Code)

Max Activating Token Index: 229