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

Dataset: The Pile

Neuron 838 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2931. Min Act: -0.0000

Data Index: 914685 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2568. Min Act: -0.0000

Data Index: 955121 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1430343 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1413427 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1309111 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1908495 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2601. Min Act: -0.0000

Data Index: 177484 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2075. Min Act: -0.0000

Data Index: 639582 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1751891 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1708794 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1119882 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1616184 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1246466 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1710128 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2048. Min Act: -0.0000

Data Index: 851999 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1871843 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1192620 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.1916. Min Act: -0.0000

Data Index: 812885 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1669816 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.1839. Min Act: -0.0000

Data Index: 292756 (The Pile)

Max Activating Token Index: 30