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

Dataset: The Pile

Neuron 1881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5214. Min Act: -0.0000

Data Index: 790138 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1416788 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1847975 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1983212 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5461. Min Act: -0.0000

Data Index: 685017 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5612. Min Act: -0.0000

Data Index: 123431 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1553315 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1339393 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1707521 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4360. Min Act: -0.0000

Data Index: 562416 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5041. Min Act: -0.0000

Data Index: 684917 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4546. Min Act: -0.0000

Data Index: 956308 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1405481 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4181. Min Act: -0.0000

Data Index: 946850 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1934895 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1471307 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4693. Min Act: -0.0000

Data Index: 598628 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.3784. Min Act: -0.0000

Data Index: 119876 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.4076. Min Act: -0.0000

Data Index: 966466 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.3953. Min Act: -0.0000

Data Index: 474071 (The Pile)

Max Activating Token Index: 996