Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.5581. Min Act: -0.0001

Data Index: 321852 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.5329. Min Act: -0.0001

Data Index: 744430 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.5465. Min Act: -0.0001

Data Index: 578671 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.5222. Min Act: -0.0001

Data Index: 141547 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4991. Min Act: -0.0001

Data Index: 697534 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4641. Min Act: -0.0001

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1080686 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4205. Min Act: -0.0001

Data Index: 112256 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3991. Min Act: -0.0001

Data Index: 896469 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4109. Min Act: -0.0001

Data Index: 158826 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1269686 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3882. Min Act: -0.0001

Data Index: 146205 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3839. Min Act: -0.0001

Data Index: 354013 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3943. Min Act: -0.0001

Data Index: 241865 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3821. Min Act: -0.0001

Data Index: 746567 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3512. Min Act: -0.0001

Data Index: 1213303 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1001266 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3958. Min Act: -0.0001

Data Index: 1231346 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.5581. Min Range: -0.5581

Max Act: 0.3753. Min Act: -0.0001

Data Index: 364739 (C4 (Web Text))

Max Activating Token Index: 581