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

Dataset: The Pile

Neuron 2779 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: 0.7191. Min Range: -0.7191

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1216878 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5813. Min Act: -0.0000

Data Index: 62976 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5665. Min Act: 0.0000

Data Index: 1765308 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5219. Min Act: -0.0000

Data Index: 702432 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1820398 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5264. Min Act: -0.0000

Data Index: 514947 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1222942 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5190. Min Act: -0.0000

Data Index: 713337 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1274371 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4866. Min Act: -0.0000

Data Index: 562162 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1685982 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4859. Min Act: 0.0000

Data Index: 637483 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1831859 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4930. Min Act: -0.0000

Data Index: 11833 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1153295 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1786607 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1568231 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4880. Min Act: 0.0000

Data Index: 1271025 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1541062 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 0.7191. Min Range: -0.7191

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1875433 (The Pile)

Max Activating Token Index: 620