Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1018812 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1440377 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1144008 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4441. Min Act: -0.0000

Data Index: 990596 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1931607 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4152. Min Act: -0.0000

Data Index: 12580 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1031985 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1164289 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3834. Min Act: -0.0000

Data Index: 315541 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4061. Min Act: -0.0000

Data Index: 796408 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3815. Min Act: -0.0000

Data Index: 653282 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4416. Min Act: -0.0000

Data Index: 203318 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1289175 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1828394 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3854. Min Act: -0.0000

Data Index: 537888 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1873699 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4004. Min Act: -0.0000

Data Index: 505733 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3997. Min Act: -0.0000

Data Index: 470290 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3704. Min Act: -0.0000

Data Index: 851594 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1482724 (The Pile)

Max Activating Token Index: 944