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

Dataset: The Pile

Neuron 1421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1693383 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1293533 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4573. Min Act: -0.0000

Data Index: 760401 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1039854 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1917227 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4320. Min Act: -0.0000

Data Index: 917734 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1584616 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1787749 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1573041 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4349. Min Act: -0.0000

Data Index: 688324 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1903139 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1514375 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1204357 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1675975 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1366826 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4340. Min Act: -0.0000

Data Index: 503726 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4316. Min Act: -0.0000

Data Index: 728310 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4190. Min Act: -0.0000

Data Index: 830105 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1729894 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 0.5160. Min Range: -0.5160

Max Act: 0.4140. Min Act: -0.0000

Data Index: 916638 (The Pile)

Max Activating Token Index: 73