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

Dataset: The Pile

Neuron 594 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1781722 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1666747 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1555958 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1717344 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4167. Min Act: -0.0000

Data Index: 723499 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4216. Min Act: -0.0000

Data Index: 975259 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.4180. Min Act: -0.0000

Data Index: 900201 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1885358 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3573. Min Act: -0.0000

Data Index: 707418 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3682. Min Act: -0.0000

Data Index: 814218 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1772473 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3560. Min Act: -0.0000

Data Index: 819418 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3679. Min Act: -0.0000

Data Index: 964352 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1717160 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1253844 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3416. Min Act: -0.0000

Data Index: 242485 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1391254 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1879702 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3521. Min Act: -0.0000

Data Index: 447474 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.7151. Min Range: -0.7151

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1648654 (The Pile)

Max Activating Token Index: 383