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

Dataset: The Pile

Neuron 4419 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: 0.8803. Min Range: -0.8803

Max Act: 0.8803. Min Act: -0.0000

Data Index: 480742 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1336225 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1613946 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6158. Min Act: -0.0000

Data Index: 123091 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6333. Min Act: -0.0000

Data Index: 759194 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1651419 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6254. Min Act: -0.0000

Data Index: 904320 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1995558 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5318. Min Act: -0.0000

Data Index: 873353 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5451. Min Act: -0.0000

Data Index: 405225 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5630. Min Act: -0.0000

Data Index: 201351 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1597487 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5004. Min Act: -0.0000

Data Index: 442798 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1356772 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1375649 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5443. Min Act: -0.0000

Data Index: 489124 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5300. Min Act: -0.0000

Data Index: 776581 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4716. Min Act: -0.0000

Data Index: 118932 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4351. Min Act: 0.0000

Data Index: 758279 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5302. Min Act: -0.0000

Data Index: 785863 (The Pile)

Max Activating Token Index: 734