Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.9588. Min Act: -0.0000

Data Index: 228852 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1750379 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1662285 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7950. Min Act: -0.0000

Data Index: 485239 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1783382 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1493111 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1040155 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7126. Min Act: -0.0000

Data Index: 148474 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1900608 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1864005 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1504616 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7423. Min Act: -0.0000

Data Index: 387406 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7616. Min Act: -0.0000

Data Index: 991511 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7149. Min Act: -0.0000

Data Index: 649453 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1774829 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1517274 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7752. Min Act: -0.0000

Data Index: 412155 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7265. Min Act: -0.0000

Data Index: 188837 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1115935 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1957583 (The Pile)

Max Activating Token Index: 573