Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 623 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2301. Min Range: -3.2301

Max Act: 3.2301. Min Act: -0.0000

Data Index: 1456983 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.9084. Min Act: -0.0000

Data Index: 1585370 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.7163. Min Act: -0.0000

Data Index: 1406627 (Python Code)

Max Activating Token Index: 482

Text #3

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.8493. Min Act: -0.0000

Data Index: 1519300 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.4148. Min Act: -0.0000

Data Index: 1379296 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.1890. Min Act: -0.0000

Data Index: 744363 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.3078. Min Act: -0.0000

Data Index: 1639250 (Python Code)

Max Activating Token Index: 516

Text #7

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.0134. Min Act: -0.0000

Data Index: 1499715 (Python Code)

Max Activating Token Index: 400

Text #8

Max Range: 3.2301. Min Range: -3.2301

Max Act: 2.1424. Min Act: -0.0000

Data Index: 1595301 (Python Code)

Max Activating Token Index: 576

Text #9

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.6984. Min Act: -0.0000

Data Index: 1390460 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1426146 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1531743 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.9771. Min Act: -0.0000

Data Index: 1561292 (Python Code)

Max Activating Token Index: 422

Text #13

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.8072. Min Act: -0.0000

Data Index: 1480492 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1425300 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.9305. Min Act: -0.0000

Data Index: 1384912 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1394500 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.8204. Min Act: -0.0000

Data Index: 1540131 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.7580. Min Act: -0.0000

Data Index: 1561517 (Python Code)

Max Activating Token Index: 168

Text #19

Max Range: 3.2301. Min Range: -3.2301

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1423024 (Python Code)

Max Activating Token Index: 258