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

Dataset: The Pile

Neuron 3536 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: 0.8951. Min Range: -0.8951

Max Act: 0.8951. Min Act: -0.0000

Data Index: 536746 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7848. Min Act: -0.0000

Data Index: 871128 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8380. Min Act: -0.0000

Data Index: 577110 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7265. Min Act: -0.0000

Data Index: 830212 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1598462 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6788. Min Act: -0.0000

Data Index: 138165 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7195. Min Act: -0.0000

Data Index: 424983 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1958975 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1468847 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1666304 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1960779 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6974. Min Act: -0.0000

Data Index: 160945 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6774. Min Act: -0.0000

Data Index: 821405 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1560710 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6521. Min Act: -0.0000

Data Index: 412297 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6612. Min Act: -0.0000

Data Index: 249480 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6620. Min Act: -0.0000

Data Index: 862973 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6779. Min Act: -0.0000

Data Index: 960905 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6136. Min Act: -0.0000

Data Index: 430292 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1414773 (The Pile)

Max Activating Token Index: 533