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

Dataset: The Pile

Neuron 2582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1513. Min Act: -0.0000

Data Index: 267335 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1645. Min Act: -0.0000

Data Index: 480145 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1947730 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1527658 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1790824 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1138087 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1710314 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1584590 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1645391 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1603173 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1327822 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1587288 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1266. Min Act: -0.0000

Data Index: 493254 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1797680 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1214. Min Act: -0.0000

Data Index: 701662 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1228. Min Act: -0.0000

Data Index: 609427 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1037. Min Act: -0.0000

Data Index: 791134 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1095819 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1421071 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1407562 (The Pile)

Max Activating Token Index: 249