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

Dataset: The Pile

Neuron 1269 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1924458 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1247600 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1700152 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1517545 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1255836 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1820219 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1467940 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1446726 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1241120 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3663. Min Act: -0.0000

Data Index: 632712 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3890. Min Act: -0.0000

Data Index: 149268 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1788717 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3627. Min Act: -0.0000

Data Index: 574662 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3519. Min Act: -0.0000

Data Index: 5532 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1240424 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1498278 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1596728 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1126050 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1520056 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1492259 (The Pile)

Max Activating Token Index: 834