Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3507 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.3624. Min Act: -0.0000

Data Index: 1771421 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.0998. Min Act: -0.0000

Data Index: 1528283 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.2185. Min Act: -0.0000

Data Index: 1761338 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1761. Min Act: -0.0000

Data Index: 1994383 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.1719. Min Act: -0.0000

Data Index: 10942 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.9752. Min Act: -0.0000

Data Index: 1014835 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.9165. Min Act: -0.0000

Data Index: 391017 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.0495. Min Act: -0.0000

Data Index: 1305544 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.8806. Min Act: -0.0000

Data Index: 1606217 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 3.3624. Min Range: -3.3624

Max Act: 3.0910. Min Act: -0.0000

Data Index: 520201 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.9572. Min Act: -0.0000

Data Index: 1925845 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.9355. Min Act: -0.0000

Data Index: 165266 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.9875. Min Act: -0.0000

Data Index: 1418266 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.9234. Min Act: -0.0000

Data Index: 402054 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.8590. Min Act: -0.0000

Data Index: 997848 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.8681. Min Act: -0.0000

Data Index: 1904815 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.8652. Min Act: -0.0000

Data Index: 302149 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.6767. Min Act: -0.0000

Data Index: 897019 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.7945. Min Act: -0.0000

Data Index: 130950 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 3.3624. Min Range: -3.3624

Max Act: 2.6161. Min Act: -0.0000

Data Index: 1633965 (The Pile)

Max Activating Token Index: 63