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

Dataset: The Pile

Neuron 880 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: 1.6012. Min Range: -1.6012

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1850358 (The Pile)

Max Activating Token Index: 427

Text #1

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1382819 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.4233. Min Act: -0.0000

Data Index: 711006 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3804. Min Act: -0.0000

Data Index: 247714 (The Pile)

Max Activating Token Index: 705

Text #4

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1649387 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2772. Min Act: -0.0000

Data Index: 1715749 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1556157 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3209. Min Act: -0.0000

Data Index: 957203 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1662022 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1702655 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1592004 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2456. Min Act: -0.0000

Data Index: 643469 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3228. Min Act: -0.0000

Data Index: 14893 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1550485 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1191949 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3462. Min Act: -0.0000

Data Index: 147557 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1471846 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.3262. Min Act: -0.0000

Data Index: 537204 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.2826. Min Act: -0.0000

Data Index: 889988 (The Pile)

Max Activating Token Index: 401

Text #19

Max Range: 1.6012. Min Range: -1.6012

Max Act: 1.4190. Min Act: -0.0000

Data Index: 1517300 (The Pile)

Max Activating Token Index: 664