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

Dataset: The Pile

Neuron 3554 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.2351. Min Act: -0.0000

Data Index: 410317 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.3693. Min Act: -0.0000

Data Index: 308900 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1460427 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1517. Min Act: -0.0000

Data Index: 187267 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0912. Min Act: -0.0000

Data Index: 449216 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1203569 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1364. Min Act: -0.0000

Data Index: 256638 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1275952 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0810. Min Act: -0.0000

Data Index: 119308 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1503593 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0760. Min Act: -0.0000

Data Index: 657276 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9856. Min Act: -0.0000

Data Index: 829436 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0434. Min Act: -0.0000

Data Index: 206796 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1930922 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1063404 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1425686 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.1208. Min Act: -0.0000

Data Index: 164294 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0216. Min Act: -0.0000

Data Index: 152801 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.5168. Min Range: -1.5168

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1000937 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 1.5168. Min Range: -1.5168

Max Act: 0.9484. Min Act: -0.0000

Data Index: 415745 (The Pile)

Max Activating Token Index: 1008