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

Dataset: The Pile

Neuron 1756 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: 0.9680. Min Range: -0.9680

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1227229 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7689. Min Act: -0.0000

Data Index: 613325 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1136110 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8168. Min Act: -0.0000

Data Index: 480981 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1888246 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1164512 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1492031 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6262. Min Act: -0.0000

Data Index: 413735 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6407. Min Act: -0.0000

Data Index: 332438 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1694513 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1935111 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1343134 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1693319 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1106312 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5781. Min Act: -0.0000

Data Index: 385086 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5645. Min Act: -0.0000

Data Index: 506391 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1139111 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1446803 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5371. Min Act: -0.0000

Data Index: 710953 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1805708 (The Pile)

Max Activating Token Index: 701