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

Dataset: The Pile

Neuron 823 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: 3.0048. Min Range: -3.0048

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1961729 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.4321. Min Act: -0.0000

Data Index: 1254756 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.5651. Min Act: -0.0000

Data Index: 522547 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.5032. Min Act: -0.0000

Data Index: 1649790 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.5216. Min Act: -0.0000

Data Index: 1382403 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2743. Min Act: -0.0000

Data Index: 815028 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.7719. Min Act: -0.0000

Data Index: 1496617 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.4693. Min Act: -0.0000

Data Index: 937553 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.3399. Min Act: -0.0000

Data Index: 646790 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.4440. Min Act: -0.0000

Data Index: 382008 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.1835. Min Act: -0.0000

Data Index: 1233376 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.4194. Min Act: -0.0000

Data Index: 10138 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2870. Min Act: -0.0000

Data Index: 1947952 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.3806. Min Act: -0.0000

Data Index: 434013 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.6124. Min Act: -0.0000

Data Index: 51957 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2535. Min Act: -0.0000

Data Index: 461557 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2526. Min Act: -0.0000

Data Index: 499641 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2512. Min Act: -0.0000

Data Index: 192266 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.4653. Min Act: -0.0000

Data Index: 860944 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 3.0048. Min Range: -3.0048

Max Act: 2.2326. Min Act: -0.0000

Data Index: 873347 (The Pile)

Max Activating Token Index: 30