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

Dataset: The Pile

Neuron 3256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.4390. Min Act: -0.0000

Data Index: 495062 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3340. Min Act: -0.0000

Data Index: 73411 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1627916 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1581794 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2953. Min Act: -0.0000

Data Index: 361909 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3038. Min Act: -0.0000

Data Index: 56853 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3098. Min Act: -0.0000

Data Index: 340195 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1286470 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2746. Min Act: -0.0000

Data Index: 965215 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1933809 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1960711 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1841165 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2727. Min Act: -0.0000

Data Index: 642061 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2627. Min Act: -0.0000

Data Index: 554434 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2607. Min Act: -0.0000

Data Index: 718380 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2432. Min Act: -0.0000

Data Index: 861404 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1018345 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1539206 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1976068 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1277424 (The Pile)

Max Activating Token Index: 1015