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

Dataset: The Pile

Neuron 2339 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: 1.1611. Min Range: -1.1611

Max Act: 1.1611. Min Act: -0.0000

Data Index: 642880 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1825257 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1611654 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9274. Min Act: -0.0000

Data Index: 949139 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9308. Min Act: -0.0000

Data Index: 111822 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1929114 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8859. Min Act: -0.0000

Data Index: 523483 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0394. Min Act: -0.0000

Data Index: 578164 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8748. Min Act: -0.0000

Data Index: 670727 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1141600 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9079. Min Act: -0.0000

Data Index: 371673 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8300. Min Act: -0.0000

Data Index: 996584 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1167725 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8512. Min Act: -0.0000

Data Index: 428313 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1428317 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1616986 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.7888. Min Act: -0.0000

Data Index: 886330 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1597032 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1237975 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9084. Min Act: -0.0000

Data Index: 35898 (The Pile)

Max Activating Token Index: 140