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

Dataset: The Pile

Neuron 4183 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0954. Min Act: -0.0000

Data Index: 523117 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1605302 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1305729 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1945412 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1131219 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1904293 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1749102 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1817028 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9490. Min Act: -0.0000

Data Index: 190887 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1693251 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1297029 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1195464 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1120858 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9312. Min Act: -0.0000

Data Index: 970689 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9538. Min Act: -0.0000

Data Index: 139482 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1953154 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1145603 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1086710 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8963. Min Act: -0.0000

Data Index: 511448 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9167. Min Act: -0.0000

Data Index: 194874 (The Pile)

Max Activating Token Index: 769