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

Dataset: The Pile

Neuron 2593 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: 1.2100. Min Range: -1.2100

Max Act: 1.2100. Min Act: -0.0000

Data Index: 939512 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8922. Min Act: -0.0000

Data Index: 615891 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.9147. Min Act: -0.0000

Data Index: 485470 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1141355 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1870123 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8293. Min Act: -0.0000

Data Index: 70806 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1669129 (The Pile)

Max Activating Token Index: 635

Text #7

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1980122 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8333. Min Act: -0.0001

Data Index: 800715 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.8301. Min Act: -0.0000

Data Index: 831509 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7731. Min Act: -0.0000

Data Index: 491076 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1952106 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1906391 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7629. Min Act: -0.0000

Data Index: 213631 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1472272 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1463027 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1342332 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1625502 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1001725 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 1.2100. Min Range: -1.2100

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1768293 (The Pile)

Max Activating Token Index: 228