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

Dataset: The Pile

Neuron 3564 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: 1.4096. Min Range: -1.4096

Max Act: 1.4096. Min Act: 0.0000

Data Index: 124329 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1083656 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.3298. Min Act: 0.0000

Data Index: 801930 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1988212 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1671. Min Act: -0.0000

Data Index: 911683 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1692. Min Act: 0.0000

Data Index: 613350 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1207747 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2280. Min Act: 0.0000

Data Index: 1706589 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1852. Min Act: -0.0000

Data Index: 777385 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1352451 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0956. Min Act: -0.0000

Data Index: 215635 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1437. Min Act: 0.0001

Data Index: 1361181 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1008618 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1786362 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1458136 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9548. Min Act: -0.0000

Data Index: 631331 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1466932 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0037. Min Act: -0.0000

Data Index: 776387 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9941. Min Act: -0.0000

Data Index: 959205 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1477115 (The Pile)

Max Activating Token Index: 996