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

Dataset: The Pile

Neuron 1008 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: 0.5321. Min Range: -0.5321

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1356852 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4409. Min Act: -0.0000

Data Index: 901929 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1080390 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4600. Min Act: -0.0000

Data Index: 800654 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1069555 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4374. Min Act: -0.0000

Data Index: 104151 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4098. Min Act: -0.0000

Data Index: 401341 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4127. Min Act: -0.0000

Data Index: 226098 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4193. Min Act: -0.0000

Data Index: 543289 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1905624 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4282. Min Act: -0.0000

Data Index: 636005 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1423602 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4109. Min Act: -0.0000

Data Index: 468035 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1865528 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3855. Min Act: -0.0000

Data Index: 352163 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1573519 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3822. Min Act: -0.0000

Data Index: 131691 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1625055 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3608. Min Act: -0.0000

Data Index: 767899 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3876. Min Act: -0.0000

Data Index: 588015 (The Pile)

Max Activating Token Index: 256