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

Dataset: The Pile

Neuron 5054 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1986159 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0608. Min Act: -0.0000

Data Index: 511636 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0600. Min Act: -0.0000

Data Index: 464710 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0599. Min Act: -0.0000

Data Index: 240310 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0591. Min Act: -0.0000

Data Index: 454215 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1491759 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0582. Min Act: -0.0000

Data Index: 15698 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0573. Min Act: -0.0000

Data Index: 682189 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0563. Min Act: -0.0000

Data Index: 312375 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1458700 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0559. Min Act: -0.0000

Data Index: 355014 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1429852 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1223268 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0549. Min Act: -0.0000

Data Index: 278907 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1587617 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0547. Min Act: -0.0000

Data Index: 402155 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0546. Min Act: -0.0000

Data Index: 353425 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1879594 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0542. Min Act: -0.0000

Data Index: 708603 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0535. Min Act: -0.0000

Data Index: 981010 (The Pile)

Max Activating Token Index: 247