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

Dataset: The Pile

Neuron 4141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3647. Min Range: -5.3647

Max Act: 5.3522. Min Act: -0.0000

Data Index: 122538 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 5.3647. Min Range: -5.3647

Max Act: 5.1681. Min Act: -0.0000

Data Index: 1702079 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 5.3647. Min Range: -5.3647

Max Act: 5.2191. Min Act: -0.0000

Data Index: 1259586 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.8076. Min Act: -0.0000

Data Index: 735875 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 5.3647. Min Range: -5.3647

Max Act: 5.3647. Min Act: -0.0000

Data Index: 1589831 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.4422. Min Act: -0.0000

Data Index: 115833 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.8970. Min Act: -0.0000

Data Index: 950202 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.5654. Min Act: -0.0000

Data Index: 1792872 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.4383. Min Act: -0.0000

Data Index: 1031987 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.4796. Min Act: -0.0000

Data Index: 458187 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.4320. Min Act: -0.0000

Data Index: 737930 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.5569. Min Act: -0.0000

Data Index: 799494 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.3620. Min Act: -0.0000

Data Index: 261447 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.3392. Min Act: -0.0000

Data Index: 1058635 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.2847. Min Act: -0.0000

Data Index: 587832 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.1450. Min Act: -0.0000

Data Index: 1264899 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.4346. Min Act: -0.0000

Data Index: 275573 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 5.3647. Min Range: -5.3647

Max Act: 3.9347. Min Act: -0.0000

Data Index: 1605847 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 5.3647. Min Range: -5.3647

Max Act: 3.9364. Min Act: -0.0000

Data Index: 1290705 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 5.3647. Min Range: -5.3647

Max Act: 4.2703. Min Act: -0.0000

Data Index: 550053 (The Pile)

Max Activating Token Index: 428