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

Dataset: The Pile

Neuron 2090 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.7112. Min Act: 0.0000

Data Index: 1353106 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.8173. Min Act: -0.0000

Data Index: 6239 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 4.0482. Min Range: -4.0482

Max Act: 4.0482. Min Act: -0.0000

Data Index: 455175 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.4883. Min Act: -0.0000

Data Index: 449574 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.6757. Min Act: -0.0000

Data Index: 1219171 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.6216. Min Act: -0.0000

Data Index: 1108671 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.6093. Min Act: -0.0000

Data Index: 858844 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.6657. Min Act: -0.0000

Data Index: 1855325 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.3421. Min Act: -0.0000

Data Index: 1624168 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.3610. Min Act: -0.0000

Data Index: 1904903 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.3042. Min Act: -0.0000

Data Index: 488491 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.4163. Min Act: -0.0000

Data Index: 1199413 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.5022. Min Act: -0.0000

Data Index: 751075 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.1800. Min Act: -0.0000

Data Index: 559508 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.1840. Min Act: -0.0000

Data Index: 72579 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.1455. Min Act: -0.0000

Data Index: 1649549 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.4617. Min Act: -0.0000

Data Index: 1606459 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.5186. Min Act: -0.0000

Data Index: 1251071 (The Pile)

Max Activating Token Index: 27

Text #18

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.1077. Min Act: -0.0000

Data Index: 1257902 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 4.0482. Min Range: -4.0482

Max Act: 3.5040. Min Act: -0.0000

Data Index: 432941 (The Pile)

Max Activating Token Index: 698