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

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

Neuron 416 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.3119. Min Act: -0.0001

Data Index: 328496 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1255674 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2615. Min Act: -0.0001

Data Index: 933741 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2293. Min Act: -0.0001

Data Index: 703528 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.1836. Min Act: -0.0001

Data Index: 746365 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2551. Min Act: -0.0001

Data Index: 529483 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2255. Min Act: -0.0001

Data Index: 729904 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2488. Min Act: -0.0001

Data Index: 835794 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2375. Min Act: -0.0001

Data Index: 707636 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1272545 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2491. Min Act: -0.0001

Data Index: 56757 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2048. Min Act: -0.0001

Data Index: 849406 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2796. Min Act: -0.0001

Data Index: 82220 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2561. Min Act: -0.0001

Data Index: 293210 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2454. Min Act: -0.0001

Data Index: 218535 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2290. Min Act: -0.0001

Data Index: 424265 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2281. Min Act: -0.0001

Data Index: 748563 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2410. Min Act: -0.0001

Data Index: 786952 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2323. Min Act: -0.0001

Data Index: 143725 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2345. Min Act: -0.0001

Data Index: 813893 (C4 (Web Text))

Max Activating Token Index: 165