Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 169 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: -0.0001

Data Index: 3454 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1106108 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6096. Min Act: -0.0001

Data Index: 1120417 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1281206 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6124. Min Act: -0.0001

Data Index: 481864 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5945. Min Act: -0.0001

Data Index: 33002 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1015988 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5809. Min Act: -0.0001

Data Index: 701746 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5982. Min Act: -0.0001

Data Index: 79582 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5890. Min Act: -0.0001

Data Index: 534842 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5799. Min Act: 0.0001

Data Index: 1113739 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5966. Min Act: -0.0001

Data Index: 715435 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5701. Min Act: -0.0001

Data Index: 172820 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5819. Min Act: -0.0001

Data Index: 946179 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5385. Min Act: -0.0001

Data Index: 1188187 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5720. Min Act: -0.0001

Data Index: 596427 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1272210 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5101. Min Act: -0.0000

Data Index: 794974 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5642. Min Act: -0.0001

Data Index: 1225626 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5184. Min Act: -0.0001

Data Index: 703116 (C4 (Web Text))

Max Activating Token Index: 141