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

Dataset: The Pile

Neuron 1805 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: 0.3787. Min Range: -0.3787

Max Act: 0.3598. Min Act: -0.0000

Data Index: 548369 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3787. Min Act: -0.0000

Data Index: 498177 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1162339 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1887019 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1835264 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3673. Min Act: -0.0000

Data Index: 302122 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1465625 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1554131 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3426. Min Act: -0.0000

Data Index: 641256 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1888351 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3263. Min Act: -0.0000

Data Index: 976610 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3153. Min Act: -0.0000

Data Index: 869284 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1457376 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3426. Min Act: -0.0000

Data Index: 950017 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1435914 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1883993 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3021. Min Act: -0.0000

Data Index: 774133 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1617741 (The Pile)

Max Activating Token Index: 947

Text #18

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1550034 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3044. Min Act: -0.0000

Data Index: 272585 (The Pile)

Max Activating Token Index: 158