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

Dataset: The Pile

Neuron 4851 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6434. Min Act: -0.0000

Data Index: 644251 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8867. Min Act: -0.0000

Data Index: 397197 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1237581 (The Pile)

Max Activating Token Index: 687

Text #3

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.3983. Min Act: -0.0000

Data Index: 300073 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.3528. Min Act: -0.0000

Data Index: 636664 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1548091 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1429037 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1604337 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.3681. Min Act: -0.0000

Data Index: 358265 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1559698 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.3005. Min Act: -0.0000

Data Index: 179127 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1373265 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1182029 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1625418 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1642297 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1117329 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1433763 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1449494 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2467. Min Act: -0.0000

Data Index: 705419 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1094646 (The Pile)

Max Activating Token Index: 496