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

Dataset: The Pile

Neuron 3692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.4249. Min Act: -0.0000

Data Index: 578440 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1772136 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3751. Min Act: -0.0000

Data Index: 475979 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1511852 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3490. Min Act: -0.0000

Data Index: 789833 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1289198 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1756023 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2690. Min Act: -0.0000

Data Index: 233313 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3497. Min Act: -0.0000

Data Index: 825145 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1756323 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3568. Min Act: -0.0000

Data Index: 981061 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1905256 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1628362 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1169996 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1438658 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3594. Min Act: -0.0000

Data Index: 539552 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.2874. Min Act: -0.0000

Data Index: 707867 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1108136 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3527. Min Act: -0.0000

Data Index: 713526 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.4249. Min Range: -0.4249

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1910279 (The Pile)

Max Activating Token Index: 645