Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 415 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0002

Data Index: 547818 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1452. Min Act: -0.0002

Data Index: 1589466 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1528170 (Python Code)

Max Activating Token Index: 784

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1494. Min Act: -0.0002

Data Index: 372626 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1556038 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1472. Min Act: -0.0002

Data Index: 238630 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1329. Min Act: -0.0002

Data Index: 962953 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1452037 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1357610 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1266. Min Act: -0.0002

Data Index: 929237 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1409874 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1646891 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1192. Min Act: -0.0002

Data Index: 808097 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1179. Min Act: -0.0002

Data Index: 714469 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1566614 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1206. Min Act: -0.0002

Data Index: 565987 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1172. Min Act: -0.0002

Data Index: 553412 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1362329 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1311449 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1094. Min Act: -0.0002

Data Index: 928759 (C4 (Web Text))

Max Activating Token Index: 410