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

Dataset: The Pile

Neuron 3179 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9392. Min Range: -5.9392

Max Act: 5.9392. Min Act: -0.0000

Data Index: 893806 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 5.9392. Min Range: -5.9392

Max Act: 5.7429. Min Act: -0.0000

Data Index: 1372046 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 5.9392. Min Range: -5.9392

Max Act: 5.2163. Min Act: -0.0000

Data Index: 1528367 (The Pile)

Max Activating Token Index: 474

Text #3

Max Range: 5.9392. Min Range: -5.9392

Max Act: 4.7015. Min Act: -0.0000

Data Index: 472972 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 5.9392. Min Range: -5.9392

Max Act: 4.5658. Min Act: -0.0000

Data Index: 946351 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 5.9392. Min Range: -5.9392

Max Act: 4.3717. Min Act: -0.0000

Data Index: 1278437 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 5.9392. Min Range: -5.9392

Max Act: 4.3316. Min Act: -0.0000

Data Index: 1999151 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 5.9392. Min Range: -5.9392

Max Act: 4.3380. Min Act: -0.0000

Data Index: 401636 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.8474. Min Act: -0.0000

Data Index: 829728 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.8742. Min Act: -0.0000

Data Index: 1337624 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.9126. Min Act: -0.0000

Data Index: 963904 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.5421. Min Act: -0.0000

Data Index: 1662250 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.4939. Min Act: -0.0000

Data Index: 1631335 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.6247. Min Act: -0.0000

Data Index: 1075175 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.4553. Min Act: -0.0000

Data Index: 1115763 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.2699. Min Act: -0.0000

Data Index: 1220155 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.5679. Min Act: -0.0000

Data Index: 1260471 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.3954. Min Act: -0.0000

Data Index: 317994 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.3002. Min Act: 0.0000

Data Index: 1011402 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 5.9392. Min Range: -5.9392

Max Act: 3.0633. Min Act: 0.0001

Data Index: 1216994 (The Pile)

Max Activating Token Index: 7