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

Dataset: The Pile

Neuron 3317 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: 1.0635. Min Range: -1.0635

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1472704 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9345. Min Act: -0.0000

Data Index: 464584 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1137515 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1614900 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1310459 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8359. Min Act: -0.0000

Data Index: 105459 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8972. Min Act: -0.0000

Data Index: 171759 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1532887 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1527312 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8547. Min Act: -0.0000

Data Index: 729822 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1115586 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9038. Min Act: -0.0000

Data Index: 812575 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1567325 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8337. Min Act: -0.0000

Data Index: 223719 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8103. Min Act: -0.0000

Data Index: 612261 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1512755 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8018. Min Act: -0.0000

Data Index: 184998 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1656085 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8222. Min Act: -0.0000

Data Index: 139598 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1975626 (The Pile)

Max Activating Token Index: 404