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

Dataset: The Pile

Neuron 1454 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: 0.7451. Min Range: -0.7451

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1193180 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1482040 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1098972 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1287376 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1184934 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6143. Min Act: -0.0000

Data Index: 965009 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5853. Min Act: -0.0000

Data Index: 563012 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1278054 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5800. Min Act: -0.0000

Data Index: 593173 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5307. Min Act: -0.0000

Data Index: 695732 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1892245 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5155. Min Act: -0.0000

Data Index: 294095 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4808. Min Act: -0.0000

Data Index: 390525 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1905843 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1676055 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1185704 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4848. Min Act: -0.0000

Data Index: 990425 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1866138 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1795229 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4991. Min Act: -0.0000

Data Index: 624499 (The Pile)

Max Activating Token Index: 782