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

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

Neuron 3185 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1230765 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1311495 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.2164. Min Act: -0.0000

Data Index: 504057 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1787. Min Act: -0.0000

Data Index: 507069 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1066995 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1616. Min Act: -0.0000

Data Index: 101493 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1711. Min Act: -0.0000

Data Index: 945832 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1296219 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1852. Min Act: -0.0000

Data Index: 889040 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1638263 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1651. Min Act: -0.0000

Data Index: 403362 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1615958 (Python Code)

Max Activating Token Index: 938

Text #12

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1615. Min Act: -0.0000

Data Index: 591562 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1625608 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1604. Min Act: -0.0000

Data Index: 243549 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1566. Min Act: -0.0000

Data Index: 996483 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1459. Min Act: -0.0000

Data Index: 762875 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1636575 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1325. Min Act: -0.0000

Data Index: 279661 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1374. Min Act: -0.0000

Data Index: 924385 (C4 (Web Text))

Max Activating Token Index: 427