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

Dataset: The Pile

Neuron 2138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3701. Min Act: -0.0000

Data Index: 1964190 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3978. Min Act: -0.0000

Data Index: 1158818 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.3343. Min Act: -0.0000

Data Index: 1637785 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1254. Min Act: -0.0000

Data Index: 1426002 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.2030. Min Act: -0.0000

Data Index: 1842186 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9735. Min Act: -0.0000

Data Index: 1928518 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9541. Min Act: -0.0000

Data Index: 1804082 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0690. Min Act: 0.0000

Data Index: 1997127 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9326. Min Act: -0.0000

Data Index: 1153437 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.1016. Min Act: -0.0000

Data Index: 1793832 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9288. Min Act: 0.0000

Data Index: 128133 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0603. Min Act: -0.0000

Data Index: 999017 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9074. Min Act: 0.0002

Data Index: 639322 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0811. Min Act: -0.0000

Data Index: 1267880 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0396. Min Act: -0.0000

Data Index: 678201 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 3.3978. Min Range: -3.3978

Max Act: 3.0369. Min Act: -0.0000

Data Index: 1953932 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9899. Min Act: -0.0000

Data Index: 624399 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.8647. Min Act: -0.0000

Data Index: 955321 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.7141. Min Act: -0.0000

Data Index: 1158746 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 3.3978. Min Range: -3.3978

Max Act: 2.9586. Min Act: -0.0000

Data Index: 460363 (The Pile)

Max Activating Token Index: 863