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

Dataset: The Pile

Neuron 2656 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.2046. Min Act: -0.0000

Data Index: 41295 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.0286. Min Act: -0.0000

Data Index: 905421 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9431. Min Act: -0.0000

Data Index: 703647 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1126159 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1532967 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8902. Min Act: -0.0000

Data Index: 882477 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1364940 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9132. Min Act: -0.0000

Data Index: 265963 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7983. Min Act: -0.0000

Data Index: 716870 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1519075 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7893. Min Act: -0.0000

Data Index: 199582 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8878. Min Act: -0.0000

Data Index: 31082 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1277173 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1118699 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8803. Min Act: -0.0000

Data Index: 184903 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8307. Min Act: -0.0000

Data Index: 613052 (The Pile)

Max Activating Token Index: 787

Text #16

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1663442 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8093. Min Act: -0.0000

Data Index: 42708 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7646. Min Act: -0.0000

Data Index: 760612 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1046429 (The Pile)

Max Activating Token Index: 742