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

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

Neuron 2967 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: 2.8069. Min Range: -2.8069

Max Act: 2.8069. Min Act: -0.0000

Data Index: 1470982 (Python Code)

Max Activating Token Index: 910

Text #1

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2167. Min Act: -0.0000

Data Index: 1522051 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.2533. Min Act: -0.0000

Data Index: 1388192 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 2.8069. Min Range: -2.8069

Max Act: 2.1009. Min Act: -0.0000

Data Index: 1577225 (Python Code)

Max Activating Token Index: 728

Text #4

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.9504. Min Act: -0.0000

Data Index: 1579605 (Python Code)

Max Activating Token Index: 837

Text #5

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.9630. Min Act: -0.0000

Data Index: 1398642 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1498244 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.8817. Min Act: -0.0000

Data Index: 1373888 (Python Code)

Max Activating Token Index: 265

Text #8

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.8250. Min Act: -0.0000

Data Index: 1609355 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.6931. Min Act: -0.0000

Data Index: 1459535 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1607089 (Python Code)

Max Activating Token Index: 279

Text #11

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1535823 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1613468 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.7152. Min Act: -0.0000

Data Index: 1651735 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1563494 (Python Code)

Max Activating Token Index: 234

Text #15

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1367712 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.6803. Min Act: -0.0000

Data Index: 1633732 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1449187 (Python Code)

Max Activating Token Index: 313

Text #18

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1624336 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 2.8069. Min Range: -2.8069

Max Act: 1.5365. Min Act: -0.0000

Data Index: 1620551 (Python Code)

Max Activating Token Index: 286