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

Dataset: The Pile

Neuron 1271 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: 5.4720. Min Range: -5.4720

Max Act: 5.4720. Min Act: -0.0000

Data Index: 1562042 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.2484. Min Act: -0.0000

Data Index: 1897042 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 5.4720. Min Range: -5.4720

Max Act: 3.0907. Min Act: -0.0000

Data Index: 1320934 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.4940. Min Act: -0.0000

Data Index: 117167 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.1481. Min Act: -0.0000

Data Index: 46274 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.3710. Min Act: -0.0000

Data Index: 1091814 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.1109. Min Act: -0.0000

Data Index: 632624 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.6788. Min Act: -0.0000

Data Index: 993017 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.1903. Min Act: -0.0000

Data Index: 1807860 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.0377. Min Act: -0.0000

Data Index: 689989 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.3414. Min Act: -0.0000

Data Index: 555616 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.3099. Min Act: -0.0000

Data Index: 1400636 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.4138. Min Act: -0.0000

Data Index: 633827 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.6151. Min Act: -0.0000

Data Index: 1692635 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.7480. Min Act: -0.0000

Data Index: 296369 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.3440. Min Act: -0.0000

Data Index: 1625215 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.2172. Min Act: -0.0000

Data Index: 758649 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.0977. Min Act: -0.0000

Data Index: 795575 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 5.4720. Min Range: -5.4720

Max Act: 1.9637. Min Act: -0.0000

Data Index: 509097 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 5.4720. Min Range: -5.4720

Max Act: 2.1533. Min Act: -0.0000

Data Index: 224668 (The Pile)

Max Activating Token Index: 468