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

Dataset: The Pile

Neuron 4042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1594634 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6618. Min Act: -0.0000

Data Index: 54985 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6678. Min Act: -0.0000

Data Index: 98939 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1583181 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5470. Min Act: -0.0000

Data Index: 195286 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1931804 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1466855 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1505776 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1411243 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5151. Min Act: -0.0000

Data Index: 756877 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5081. Min Act: -0.0000

Data Index: 531820 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1803748 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4759. Min Act: -0.0000

Data Index: 816865 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1379394 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1846488 (The Pile)

Max Activating Token Index: 887

Text #15

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4999. Min Act: -0.0000

Data Index: 772945 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4551. Min Act: -0.0000

Data Index: 625522 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4661. Min Act: -0.0000

Data Index: 540230 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4763. Min Act: -0.0000

Data Index: 679310 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4546. Min Act: -0.0000

Data Index: 89299 (The Pile)

Max Activating Token Index: 527