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

Dataset: The Pile

Neuron 61 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1845. Min Range: -4.1845

Max Act: 4.0735. Min Act: -0.0000

Data Index: 1480105 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.9909. Min Act: -0.0000

Data Index: 1537987 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 4.1845. Min Range: -4.1845

Max Act: 4.1845. Min Act: -0.0000

Data Index: 767413 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 4.1845. Min Range: -4.1845

Max Act: 4.0274. Min Act: -0.0000

Data Index: 838820 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.6947. Min Act: -0.0000

Data Index: 719688 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.8194. Min Act: -0.0000

Data Index: 1114369 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.6323. Min Act: -0.0000

Data Index: 630704 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.7748. Min Act: -0.0000

Data Index: 556942 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.9544. Min Act: -0.0000

Data Index: 504678 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.9284. Min Act: -0.0000

Data Index: 1030199 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.7418. Min Act: -0.0000

Data Index: 1666335 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.5536. Min Act: -0.0000

Data Index: 1712930 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.5290. Min Act: -0.0000

Data Index: 1984056 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.8722. Min Act: -0.0000

Data Index: 102553 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.5528. Min Act: -0.0000

Data Index: 1699106 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.5252. Min Act: -0.0000

Data Index: 1480591 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.6544. Min Act: -0.0000

Data Index: 768924 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.6573. Min Act: -0.0000

Data Index: 494523 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.6690. Min Act: -0.0000

Data Index: 1810016 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.4903. Min Act: -0.0000

Data Index: 577286 (The Pile)

Max Activating Token Index: 400