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

Dataset: The Pile

Neuron 4342 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: 0.8268. Min Range: -0.8268

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1487014 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7419. Min Act: -0.0000

Data Index: 608194 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1415109 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6497. Min Act: -0.0000

Data Index: 601329 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6678. Min Act: -0.0000

Data Index: 83533 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1361972 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1376926 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1247921 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6936. Min Act: -0.0000

Data Index: 804989 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1558165 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6615. Min Act: -0.0000

Data Index: 871444 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6589. Min Act: -0.0000

Data Index: 669924 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1542002 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1824977 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6108. Min Act: -0.0000

Data Index: 608020 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.5613. Min Act: -0.0000

Data Index: 61499 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1316719 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6041. Min Act: -0.0000

Data Index: 118737 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6460. Min Act: -0.0000

Data Index: 646641 (The Pile)

Max Activating Token Index: 536