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

Dataset: The Pile

Neuron 3907 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0001

Data Index: 854268 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1762056 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1017. Min Act: -0.0001

Data Index: 106038 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0991. Min Act: -0.0001

Data Index: 648822 (The Pile)

Max Activating Token Index: 295

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0823. Min Act: -0.0001

Data Index: 498020 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0947. Min Act: -0.0001

Data Index: 813377 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0957. Min Act: -0.0001

Data Index: 837201 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0917. Min Act: -0.0000

Data Index: 488981 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0884. Min Act: -0.0000

Data Index: 533466 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0892. Min Act: -0.0001

Data Index: 213850 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0829. Min Act: -0.0001

Data Index: 368976 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0887. Min Act: -0.0000

Data Index: 828564 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1883043 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0842. Min Act: -0.0000

Data Index: 371330 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0803. Min Act: -0.0000

Data Index: 829094 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1610589 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1375206 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1468636 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1038628 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1781197 (The Pile)

Max Activating Token Index: 668