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

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

Neuron 3850 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.8642. Min Act: -0.0000

Data Index: 342489 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1215493 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1224544 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.8863. Min Act: -0.0000

Data Index: 831029 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.8200. Min Act: -0.0000

Data Index: 195189 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6782. Min Act: -0.0000

Data Index: 410314 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1158404 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6583. Min Act: 0.0000

Data Index: 166901 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6504. Min Act: -0.0000

Data Index: 185133 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6571. Min Act: -0.0000

Data Index: 163649 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6448. Min Act: -0.0000

Data Index: 881896 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6101. Min Act: -0.0000

Data Index: 47080 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6300. Min Act: -0.0000

Data Index: 970053 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1196176 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.5544. Min Act: -0.0000

Data Index: 878920 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.5622. Min Act: -0.0000

Data Index: 797871 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.6030. Min Act: -0.0000

Data Index: 842859 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.5656. Min Act: -0.0000

Data Index: 491565 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1131027 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.9153. Min Range: -0.9153

Max Act: 0.5596. Min Act: -0.0000

Data Index: 110599 (C4 (Web Text))

Max Activating Token Index: 414