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

Dataset: The Pile

Neuron 3059 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.3612. Min Act: -0.0000

Data Index: 680634 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1428520 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1416165 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1652275 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1479296 (The Pile)

Max Activating Token Index: 856

Text #5

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1553270 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1396278 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1520137 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0694. Min Act: -0.0000

Data Index: 796319 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1538057 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9165. Min Act: -0.0000

Data Index: 480163 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9040. Min Act: -0.0000

Data Index: 138637 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1938384 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1510787 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9553. Min Act: -0.0000

Data Index: 60340 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1292468 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1637166 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8616. Min Act: -0.0000

Data Index: 505907 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.3612. Min Range: -1.3612

Max Act: 1.0842. Min Act: -0.0000

Data Index: 489107 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 1.3612. Min Range: -1.3612

Max Act: 0.8469. Min Act: 0.0000

Data Index: 1141601 (The Pile)

Max Activating Token Index: 323