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

Dataset: The Pile

Neuron 1941 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: 1.2772. Min Range: -1.2772

Max Act: 1.2772. Min Act: -0.0000

Data Index: 380857 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.2380. Min Act: -0.0000

Data Index: 301361 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1040213 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1511. Min Act: -0.0000

Data Index: 659769 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1192642 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1248. Min Act: -0.0000

Data Index: 954129 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1588872 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1095. Min Act: -0.0000

Data Index: 955707 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1201966 (The Pile)

Max Activating Token Index: 901

Text #9

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1563459 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1483290 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1866984 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0427. Min Act: -0.0000

Data Index: 235823 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1015671 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1390. Min Act: -0.0000

Data Index: 889134 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1626459 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1801470 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1408811 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1344334 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1387250 (The Pile)

Max Activating Token Index: 379