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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2700 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.4055. Min Act: -0.0000

Data Index: 781211 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.2511. Min Act: -0.0000

Data Index: 653361 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.1298. Min Act: -0.0000

Data Index: 995824 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1279446 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 1.4055. Min Range: -1.4055

Max Act: 1.0827. Min Act: -0.0000

Data Index: 916857 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.9850. Min Act: -0.0000

Data Index: 472148 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.9543. Min Act: -0.0000

Data Index: 649370 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.8913. Min Act: -0.0000

Data Index: 55516 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.9499. Min Act: -0.0000

Data Index: 584529 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.8990. Min Act: -0.0000

Data Index: 828449 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1171829 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.8364. Min Act: -0.0000

Data Index: 588439 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.8583. Min Act: -0.0000

Data Index: 321305 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.7730. Min Act: -0.0000

Data Index: 560953 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.8482. Min Act: -0.0000

Data Index: 283995 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.8086. Min Act: -0.0000

Data Index: 403016 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.7310. Min Act: -0.0000

Data Index: 534339 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.7416. Min Act: -0.0000

Data Index: 690081 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1289689 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.4055. Min Range: -1.4055

Max Act: 0.7193. Min Act: -0.0000

Data Index: 152675 (C4 (Web Text))

Max Activating Token Index: 651