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

Dataset: The Pile

Neuron 691 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4297. Min Range: -6.4297

Max Act: 6.4297. Min Act: -0.0000

Data Index: 25197 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 6.4297. Min Range: -6.4297

Max Act: 6.2580. Min Act: -0.0000

Data Index: 1869083 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.9281. Min Act: -0.0000

Data Index: 114710 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.6484. Min Act: -0.0000

Data Index: 326674 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.6143. Min Act: -0.0000

Data Index: 475944 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.4637. Min Act: -0.0000

Data Index: 1609199 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.0952. Min Act: -0.0000

Data Index: 997454 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.2518. Min Act: -0.0000

Data Index: 1371875 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.2196. Min Act: -0.0000

Data Index: 1103901 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.1514. Min Act: -0.0000

Data Index: 1430646 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.1202. Min Act: -0.0000

Data Index: 200645 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.1105. Min Act: -0.0000

Data Index: 1297561 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.2795. Min Act: -0.0000

Data Index: 123472 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 6.4297. Min Range: -6.4297

Max Act: 4.8738. Min Act: -0.0000

Data Index: 805457 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.2139. Min Act: -0.0000

Data Index: 1297107 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.2182. Min Act: -0.0000

Data Index: 845154 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.0182. Min Act: -0.0000

Data Index: 570879 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 6.4297. Min Range: -6.4297

Max Act: 5.0132. Min Act: -0.0000

Data Index: 1555823 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 6.4297. Min Range: -6.4297

Max Act: 4.9817. Min Act: -0.0000

Data Index: 148590 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 6.4297. Min Range: -6.4297

Max Act: 4.7772. Min Act: -0.0000

Data Index: 1932814 (The Pile)

Max Activating Token Index: 263