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

Dataset: The Pile

Neuron 3201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.6533. Min Act: -0.0000

Data Index: 42933 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1858570 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1673746 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1780856 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.2722. Min Act: -0.0000

Data Index: 165302 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1502279 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1677361 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0300. Min Act: -0.0000

Data Index: 470848 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0315. Min Act: -0.0000

Data Index: 413494 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0053. Min Act: -0.0000

Data Index: 739065 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1232016 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0287. Min Act: -0.0000

Data Index: 778778 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1512330 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.6533. Min Range: -1.6533

Max Act: 1.0089. Min Act: -0.0000

Data Index: 196748 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1026406 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1281184 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.9599. Min Act: 0.0000

Data Index: 1432490 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.8639. Min Act: -0.0000

Data Index: 608227 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1359936 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 1.6533. Min Range: -1.6533

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1388649 (The Pile)

Max Activating Token Index: 926