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

Dataset: The Pile

Neuron 2968 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: 0.8512. Min Range: -0.8512

Max Act: 0.8512. Min Act: -0.0000

Data Index: 661128 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1023533 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1991154 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6434. Min Act: -0.0000

Data Index: 554650 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1472426 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1843418 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6408. Min Act: -0.0000

Data Index: 174186 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6400. Min Act: -0.0000

Data Index: 907085 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1601958 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5476. Min Act: -0.0000

Data Index: 529258 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5005. Min Act: -0.0000

Data Index: 720306 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5447. Min Act: -0.0000

Data Index: 312080 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1309721 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5202. Min Act: -0.0000

Data Index: 239345 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5089. Min Act: -0.0000

Data Index: 870701 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1327786 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1292987 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1972024 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5113. Min Act: -0.0000

Data Index: 946311 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.4911. Min Act: -0.0000

Data Index: 858802 (The Pile)

Max Activating Token Index: 33