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

Dataset: The Pile

Neuron 3411 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.8919. Min Act: -0.0000

Data Index: 988110 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.8401. Min Act: 0.0000

Data Index: 772380 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.8048. Min Act: -0.0000

Data Index: 819477 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1413683 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1129952 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.8236. Min Act: -0.0000

Data Index: 652539 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6137. Min Act: -0.0000

Data Index: 296432 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6943. Min Act: -0.0000

Data Index: 83526 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1484573 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1159516 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1410572 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6364. Min Act: -0.0000

Data Index: 855139 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6678. Min Act: -0.0000

Data Index: 127521 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1992147 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6010. Min Act: -0.0000

Data Index: 313403 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1480069 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6988. Min Act: -0.0000

Data Index: 495062 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.5913. Min Act: -0.0000

Data Index: 83615 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1050174 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.8919. Min Range: -0.8919

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1495360 (The Pile)

Max Activating Token Index: 344