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

Dataset: The Pile

Neuron 2111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1363523 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1919455 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6151. Min Act: -0.0000

Data Index: 463085 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5893. Min Act: -0.0000

Data Index: 301630 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1465556 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5321. Min Act: -0.0000

Data Index: 715621 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1767887 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5490. Min Act: -0.0000

Data Index: 153415 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5544. Min Act: -0.0000

Data Index: 752624 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5455. Min Act: -0.0000

Data Index: 699072 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5300. Min Act: -0.0000

Data Index: 903492 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1525933 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1974212 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1306855 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1022577 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1552594 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5379. Min Act: -0.0000

Data Index: 945448 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5355. Min Act: -0.0000

Data Index: 446970 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5124. Min Act: -0.0000

Data Index: 676824 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1113072 (The Pile)

Max Activating Token Index: 500