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

Dataset: The Pile

Neuron 3418 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: 5.9808. Min Range: -5.9808

Max Act: 5.9592. Min Act: -0.0000

Data Index: 1745574 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.5561. Min Act: -0.0000

Data Index: 1260804 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.2825. Min Act: -0.0000

Data Index: 1078630 (The Pile)

Max Activating Token Index: 859

Text #3

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.6491. Min Act: -0.0000

Data Index: 806166 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.2621. Min Act: -0.0000

Data Index: 1334902 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.7422. Min Act: -0.0000

Data Index: 1617026 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.2071. Min Act: -0.0000

Data Index: 932699 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.3973. Min Act: -0.0000

Data Index: 592013 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.3624. Min Act: -0.0000

Data Index: 1713400 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.1941. Min Act: -0.0000

Data Index: 732555 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.1930. Min Act: -0.0000

Data Index: 303830 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.1622. Min Act: -0.0000

Data Index: 913557 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.4663. Min Act: -0.0000

Data Index: 173717 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.3979. Min Act: -0.0000

Data Index: 852499 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 5.9808. Min Range: -5.9808

Max Act: 4.7959. Min Act: -0.0000

Data Index: 1476559 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.1532. Min Act: -0.0000

Data Index: 1109831 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.1313. Min Act: -0.0000

Data Index: 1557776 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.6355. Min Act: -0.0000

Data Index: 1943217 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.9808. Min Act: -0.0000

Data Index: 428257 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 5.9808. Min Range: -5.9808

Max Act: 5.0791. Min Act: -0.0000

Data Index: 1187198 (The Pile)

Max Activating Token Index: 892