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

Dataset: The Pile

Neuron 3377 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0853. Min Act: -0.0000

Data Index: 810321 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1778563 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0345. Min Act: -0.0000

Data Index: 720820 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1255972 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9646. Min Act: -0.0000

Data Index: 817733 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8244. Min Act: -0.0000

Data Index: 915131 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9151. Min Act: -0.0000

Data Index: 208029 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 1.0853. Min Range: -1.0853

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1522113 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1740862 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1010089 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1376276 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8645. Min Act: -0.0000

Data Index: 361606 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1735324 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1281587 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8882. Min Act: -0.0000

Data Index: 488999 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9135. Min Act: -0.0000

Data Index: 769433 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1328973 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9648. Min Act: -0.0000

Data Index: 753853 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.9425. Min Act: -0.0000

Data Index: 724344 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.0853. Min Range: -1.0853

Max Act: 0.8323. Min Act: -0.0000

Data Index: 877308 (The Pile)

Max Activating Token Index: 33