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

Dataset: The Pile

Neuron 2488 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: 1.4885. Min Range: -1.4885

Max Act: 1.4460. Min Act: -0.0000

Data Index: 588505 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.4885. Min Act: -0.0000

Data Index: 656993 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.4415. Min Act: -0.0000

Data Index: 173435 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1488458 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1304366 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.1529. Min Act: -0.0000

Data Index: 613967 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1799294 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1534030 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.0983. Min Act: -0.0000

Data Index: 534537 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.2483. Min Act: -0.0000

Data Index: 148071 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1068901 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1411946 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.0631. Min Act: -0.0000

Data Index: 635305 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1295552 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1721793 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1322827 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 1.4885. Min Range: -1.4885

Max Act: 0.9749. Min Act: -0.0000

Data Index: 982329 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.4885. Min Range: -1.4885

Max Act: 1.1917. Min Act: -0.0000

Data Index: 460704 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 1.4885. Min Range: -1.4885

Max Act: 0.9795. Min Act: -0.0000

Data Index: 996372 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.4885. Min Range: -1.4885

Max Act: 0.9074. Min Act: -0.0000

Data Index: 887940 (The Pile)

Max Activating Token Index: 911