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

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

Neuron 3002 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: 0.6551. Min Range: -0.6551

Max Act: 0.6548. Min Act: -0.0001

Data Index: 935046 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5942. Min Act: -0.0001

Data Index: 663712 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6551. Min Act: -0.0001

Data Index: 130446 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1171022 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5465. Min Act: -0.0001

Data Index: 1040123 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5236. Min Act: -0.0001

Data Index: 123061 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5858. Min Act: -0.0001

Data Index: 1192010 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1252861 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5449. Min Act: -0.0001

Data Index: 1165429 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5371. Min Act: -0.0001

Data Index: 1137799 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5284. Min Act: -0.0001

Data Index: 111440 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5447. Min Act: -0.0001

Data Index: 945121 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5076. Min Act: -0.0001

Data Index: 320836 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1319948 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5211. Min Act: -0.0001

Data Index: 997014 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1172627 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5033. Min Act: -0.0001

Data Index: 135595 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1158241 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4795. Min Act: -0.0001

Data Index: 297654 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4942. Min Act: -0.0001

Data Index: 382794 (C4 (Web Text))

Max Activating Token Index: 222