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

Dataset: The Pile

Neuron 3369 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: 0.8012. Min Range: -0.8012

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1478475 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7055. Min Act: -0.0000

Data Index: 96412 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1799627 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6513. Min Act: -0.0000

Data Index: 620409 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1067613 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6308. Min Act: -0.0000

Data Index: 126601 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6042. Min Act: -0.0000

Data Index: 768570 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1386942 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6311. Min Act: -0.0000

Data Index: 946179 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1313247 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1875772 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5683. Min Act: -0.0000

Data Index: 237172 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1295357 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5601. Min Act: -0.0000

Data Index: 52829 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5456. Min Act: -0.0000

Data Index: 376137 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1289401 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5396. Min Act: -0.0000

Data Index: 736145 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5227. Min Act: -0.0000

Data Index: 108799 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1967438 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1121170 (The Pile)

Max Activating Token Index: 300