Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 359 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0663. Min Range: -1.0663

Max Act: 1.0663. Min Act: -0.0000

Data Index: 329060 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.9235. Min Act: -0.0000

Data Index: 514265 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7797. Min Act: -0.0000

Data Index: 621234 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7854. Min Act: -0.0000

Data Index: 348874 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1242194 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1097429 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6075. Min Act: -0.0000

Data Index: 660714 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5950. Min Act: -0.0000

Data Index: 337064 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1594412 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6012. Min Act: -0.0000

Data Index: 654401 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5679. Min Act: -0.0000

Data Index: 276576 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1940636 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1801328 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1456409 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1634742 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1045150 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.4939. Min Act: -0.0000

Data Index: 445167 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.3748. Min Act: -0.0000

Data Index: 540273 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1336268 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1762237 (The Pile)

Max Activating Token Index: 201