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

Dataset: The Pile

Neuron 4694 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: 3.9230. Min Range: -3.9230

Max Act: 3.9230. Min Act: -0.0000

Data Index: 114366 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.8620. Min Act: -0.0000

Data Index: 1626231 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.5678. Min Act: -0.0000

Data Index: 473385 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.5904. Min Act: -0.0000

Data Index: 1430163 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.7272. Min Act: -0.0000

Data Index: 1906536 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.5677. Min Act: -0.0000

Data Index: 112381 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.2336. Min Act: -0.0000

Data Index: 1407708 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.4126. Min Act: -0.0000

Data Index: 1366897 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.4358. Min Act: -0.0000

Data Index: 1472152 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.4345. Min Act: -0.0000

Data Index: 15556 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.5354. Min Act: -0.0000

Data Index: 435396 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.4010. Min Act: -0.0000

Data Index: 1223967 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0712. Min Act: -0.0000

Data Index: 1193352 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.2760. Min Act: -0.0000

Data Index: 62021 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.4326. Min Act: -0.0000

Data Index: 1340600 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.1083. Min Act: -0.0000

Data Index: 420411 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.1492. Min Act: -0.0000

Data Index: 436406 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0890. Min Act: -0.0000

Data Index: 985072 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.1954. Min Act: -0.0000

Data Index: 422536 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.2230. Min Act: -0.0000

Data Index: 870527 (The Pile)

Max Activating Token Index: 803