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

Dataset: The Pile

Neuron 4061 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: 5.4221. Min Range: -5.4221

Max Act: 5.3238. Min Act: -0.0000

Data Index: 588048 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.7150. Min Act: -0.0000

Data Index: 113245 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 5.4221. Min Range: -5.4221

Max Act: 5.4221. Min Act: -0.0000

Data Index: 895948 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.6982. Min Act: -0.0000

Data Index: 539710 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 5.4221. Min Range: -5.4221

Max Act: 5.0164. Min Act: -0.0000

Data Index: 1435815 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.5313. Min Act: -0.0000

Data Index: 992462 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.8517. Min Act: -0.0000

Data Index: 1254343 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.1567. Min Act: -0.0000

Data Index: 656002 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.6819. Min Act: -0.0000

Data Index: 599730 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.2830. Min Act: -0.0000

Data Index: 1740645 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.3799. Min Act: -0.0000

Data Index: 378803 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.2828. Min Act: -0.0000

Data Index: 1496380 (The Pile)

Max Activating Token Index: 468

Text #12

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.4208. Min Act: -0.0000

Data Index: 1478665 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.1797. Min Act: -0.0000

Data Index: 1610936 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.3677. Min Act: -0.0000

Data Index: 1673103 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.3146. Min Act: -0.0000

Data Index: 1719865 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.4574. Min Act: -0.0000

Data Index: 1553256 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.2878. Min Act: -0.0000

Data Index: 252431 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 5.4221. Min Range: -5.4221

Max Act: 4.4237. Min Act: -0.0000

Data Index: 1988863 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 5.4221. Min Range: -5.4221

Max Act: 3.8601. Min Act: -0.0000

Data Index: 779322 (The Pile)

Max Activating Token Index: 279