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

Dataset: The Pile

Neuron 855 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: 1.9260. Min Range: -1.9260

Max Act: 1.9260. Min Act: -0.0000

Data Index: 1813739 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.8965. Min Act: -0.0000

Data Index: 1474999 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7339. Min Act: -0.0000

Data Index: 362166 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7024. Min Act: -0.0000

Data Index: 43419 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.7049. Min Act: -0.0000

Data Index: 362290 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6996. Min Act: -0.0000

Data Index: 752090 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6700. Min Act: -0.0000

Data Index: 396715 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6434. Min Act: -0.0000

Data Index: 941846 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6156. Min Act: -0.0000

Data Index: 600998 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.5319. Min Act: -0.0000

Data Index: 1717795 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.5197. Min Act: -0.0000

Data Index: 1742110 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1509131 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1288155 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1586487 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4507. Min Act: -0.0000

Data Index: 1334713 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1605818 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1303378 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1655242 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1250977 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4845. Min Act: -0.0000

Data Index: 130090 (The Pile)

Max Activating Token Index: 870