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

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

Neuron 1278 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.9695. Min Act: -0.0001

Data Index: 273354 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.5292. Min Act: -0.0000

Data Index: 871512 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.0042. Min Act: -0.0000

Data Index: 1142389 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.0732. Min Act: -0.0001

Data Index: 227490 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.0719. Min Act: -0.0000

Data Index: 698368 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.0141. Min Act: -0.0001

Data Index: 1205992 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 6.9695. Min Range: -6.9695

Max Act: 6.1439. Min Act: -0.0000

Data Index: 1320474 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.8466. Min Act: -0.0000

Data Index: 74149 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.8440. Min Act: -0.0000

Data Index: 200654 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.7797. Min Act: -0.0001

Data Index: 394049 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.8668. Min Act: -0.0001

Data Index: 1059757 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.5901. Min Act: -0.0000

Data Index: 349187 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.8671. Min Act: -0.0000

Data Index: 1126341 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.4709. Min Act: -0.0001

Data Index: 47713 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.5862. Min Act: -0.0001

Data Index: 721134 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.7713. Min Act: -0.0001

Data Index: 1172148 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.3863. Min Act: -0.0000

Data Index: 756456 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.2490. Min Act: -0.0001

Data Index: 1885 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.4921. Min Act: -0.0001

Data Index: 30842 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 6.9695. Min Range: -6.9695

Max Act: 5.2839. Min Act: -0.0000

Data Index: 56894 (C4 (Web Text))

Max Activating Token Index: 466