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

Dataset: The Pile

Neuron 4854 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.5270. Min Act: -0.0000

Data Index: 701083 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1947. Min Act: -0.0000

Data Index: 408404 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.1160. Min Act: 0.0000

Data Index: 259250 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 1.5270. Min Range: -1.5270

Max Act: 1.0683. Min Act: -0.0000

Data Index: 854618 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.9865. Min Act: -0.0000

Data Index: 779356 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1964280 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1549882 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1090779 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8769. Min Act: -0.0000

Data Index: 132295 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8468. Min Act: -0.0000

Data Index: 490822 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8740. Min Act: -0.0000

Data Index: 523003 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.7921. Min Act: -0.0000

Data Index: 559659 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8272. Min Act: -0.0000

Data Index: 249588 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8750. Min Act: -0.0000

Data Index: 894962 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1258587 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8171. Min Act: -0.0000

Data Index: 214133 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8362. Min Act: -0.0000

Data Index: 382232 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1237434 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.7959. Min Act: -0.0000

Data Index: 719580 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 1.5270. Min Range: -1.5270

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1782934 (The Pile)

Max Activating Token Index: 790