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

Dataset: The Pile

Neuron 2811 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0000

Data Index: 402177 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1637588 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4488. Min Act: -0.0000

Data Index: 455464 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1884497 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1492817 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1736244 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3949. Min Act: -0.0000

Data Index: 382899 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1996100 (The Pile)

Max Activating Token Index: 731

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4345. Min Act: -0.0000

Data Index: 842644 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3712. Min Act: -0.0000

Data Index: 46167 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1456359 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4008. Min Act: -0.0000

Data Index: 797674 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3984. Min Act: -0.0000

Data Index: 824148 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3830. Min Act: -0.0000

Data Index: 117798 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3730. Min Act: -0.0000

Data Index: 139026 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1597397 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3699. Min Act: -0.0000

Data Index: 222789 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1397403 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3836. Min Act: -0.0000

Data Index: 251858 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3940. Min Act: -0.0000

Data Index: 846960 (The Pile)

Max Activating Token Index: 534