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

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

Neuron 3243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.8145. Min Act: -0.0000

Data Index: 1534751 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.8603. Min Act: -0.0000

Data Index: 380751 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.7044. Min Act: -0.0000

Data Index: 1559550 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.5789. Min Act: -0.0000

Data Index: 333453 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1584424 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1485380 (Python Code)

Max Activating Token Index: 213

Text #6

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4765. Min Act: -0.0000

Data Index: 557586 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4560. Min Act: -0.0000

Data Index: 1385319 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1652676 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1464850 (Python Code)

Max Activating Token Index: 705

Text #10

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2808. Min Act: -0.0000

Data Index: 737384 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1608433 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3620. Min Act: -0.0000

Data Index: 1633559 (Python Code)

Max Activating Token Index: 301

Text #13

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1277975 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1441125 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1495265 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.3064. Min Act: -0.0000

Data Index: 876559 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1068304 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1539790 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 1.8603. Min Range: -1.8603

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1424961 (Python Code)

Max Activating Token Index: 700