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

Dataset: The Pile

Neuron 2247 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: 0.7697. Min Range: -0.7697

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1486024 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7599. Min Act: -0.0000

Data Index: 936737 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7356. Min Act: -0.0000

Data Index: 696311 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7458. Min Act: -0.0000

Data Index: 319778 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1360286 (The Pile)

Max Activating Token Index: 719

Text #5

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1731950 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7566. Min Act: -0.0000

Data Index: 232552 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6770. Min Act: -0.0000

Data Index: 205897 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1908435 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1234252 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6215. Min Act: -0.0000

Data Index: 151738 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1405966 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1038523 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1130586 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6625. Min Act: -0.0000

Data Index: 322466 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1789315 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6415. Min Act: -0.0000

Data Index: 730894 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6140. Min Act: -0.0000

Data Index: 311053 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6114. Min Act: -0.0000

Data Index: 55191 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6441. Min Act: -0.0000

Data Index: 448280 (The Pile)

Max Activating Token Index: 908