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

Dataset: The Pile

Neuron 1527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1310486 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1189297 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1235. Min Act: -0.0000

Data Index: 487423 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1723233 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1388581 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0952. Min Act: -0.0000

Data Index: 699633 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1514364 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1232167 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1464612 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1118928 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1927128 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1975911 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1993419 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8679. Min Act: -0.0000

Data Index: 838111 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9170. Min Act: -0.0000

Data Index: 88703 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9403. Min Act: -0.0000

Data Index: 846704 (The Pile)

Max Activating Token Index: 532

Text #16

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1838860 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9351. Min Act: -0.0001

Data Index: 1900926 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9007. Min Act: -0.0000

Data Index: 490069 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1239455 (The Pile)

Max Activating Token Index: 854