Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2607 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2127. Min Act: -0.0001

Data Index: 968557 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1302224 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1911. Min Act: -0.0001

Data Index: 750388 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2528. Min Act: -0.0001

Data Index: 661203 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2140. Min Act: -0.0001

Data Index: 568352 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2156. Min Act: -0.0001

Data Index: 735022 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1159384 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1816. Min Act: -0.0001

Data Index: 207522 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1641824 (Python Code)

Max Activating Token Index: 498

Text #9

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1749. Min Act: -0.0001

Data Index: 936992 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1885. Min Act: -0.0001

Data Index: 377428 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1344. Min Act: -0.0001

Data Index: 157202 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1561935 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1795. Min Act: -0.0001

Data Index: 329974 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1365586 (Python Code)

Max Activating Token Index: 391

Text #15

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1417081 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1277443 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1707. Min Act: -0.0001

Data Index: 714603 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1793. Min Act: -0.0001

Data Index: 830467 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1848. Min Act: -0.0001

Data Index: 628982 (C4 (Web Text))

Max Activating Token Index: 141