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

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

Neuron 1866 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1727. Min Range: -4.1727

Max Act: 4.1727. Min Act: -0.0000

Data Index: 1404955 (Python Code)

Max Activating Token Index: 678

Text #1

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.9509. Min Act: -0.0000

Data Index: 1492250 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.6900. Min Act: -0.0000

Data Index: 1564520 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.6839. Min Act: -0.0000

Data Index: 1510604 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.4775. Min Act: -0.0000

Data Index: 1571634 (Python Code)

Max Activating Token Index: 808

Text #5

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.5956. Min Act: -0.0000

Data Index: 1523559 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1397918 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.0733. Min Act: -0.0000

Data Index: 1543279 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.0604. Min Act: -0.0000

Data Index: 1423464 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.0362. Min Act: -0.0000

Data Index: 1397967 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.0204. Min Act: -0.0000

Data Index: 1560369 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.7224. Min Act: -0.0000

Data Index: 1490839 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.9563. Min Act: -0.0000

Data Index: 1431267 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.7777. Min Act: -0.0000

Data Index: 1396399 (Python Code)

Max Activating Token Index: 603

Text #14

Max Range: 4.1727. Min Range: -4.1727

Max Act: 3.0174. Min Act: -0.0000

Data Index: 1649632 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.8432. Min Act: -0.0000

Data Index: 1529337 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.6795. Min Act: -0.0000

Data Index: 1518014 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1472014 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.6741. Min Act: -0.0000

Data Index: 1500843 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 4.1727. Min Range: -4.1727

Max Act: 2.6360. Min Act: -0.0000

Data Index: 1627676 (Python Code)

Max Activating Token Index: 931