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

Dataset: The Pile

Neuron 1129 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: 0.5930. Min Range: -0.5930

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1324371 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4854. Min Act: -0.0000

Data Index: 908894 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1450762 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4694. Min Act: -0.0000

Data Index: 512287 (The Pile)

Max Activating Token Index: 167

Text #4

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4503. Min Act: -0.0000

Data Index: 16786 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4540. Min Act: -0.0000

Data Index: 358669 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4470. Min Act: -0.0000

Data Index: 751056 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4191. Min Act: 0.0000

Data Index: 986119 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4174. Min Act: -0.0000

Data Index: 908331 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1573236 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1999982 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4135. Min Act: -0.0000

Data Index: 45261 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1509575 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1363499 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3779. Min Act: -0.0000

Data Index: 16614 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1818756 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3801. Min Act: 0.0000

Data Index: 609258 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3973. Min Act: -0.0000

Data Index: 666751 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1220911 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1220862 (The Pile)

Max Activating Token Index: 273