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

Dataset: The Pile

Neuron 3547 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.8913. Min Act: -0.0001

Data Index: 845247 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1756033 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7866. Min Act: -0.0001

Data Index: 970159 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1763170 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1333369 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1246885 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7809. Min Act: -0.0001

Data Index: 1346554 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7974. Min Act: -0.0001

Data Index: 68256 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7547. Min Act: -0.0001

Data Index: 1299519 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7742. Min Act: -0.0000

Data Index: 825229 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1022950 (The Pile)

Max Activating Token Index: 778

Text #11

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7077. Min Act: -0.0000

Data Index: 267432 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7328. Min Act: -0.0000

Data Index: 748070 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1517348 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1023952 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1240850 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1157577 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7428. Min Act: -0.0000

Data Index: 699783 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1031207 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 0.8913. Min Range: -0.8913

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1425583 (The Pile)

Max Activating Token Index: 592