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

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

Neuron 2896 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: 0.8380. Min Range: -0.8380

Max Act: 0.8380. Min Act: -0.0001

Data Index: 723324 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6621. Min Act: -0.0001

Data Index: 950317 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1282007 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6583. Min Act: -0.0001

Data Index: 580777 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6560. Min Act: -0.0001

Data Index: 590993 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5978. Min Act: -0.0001

Data Index: 1222624 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6095. Min Act: -0.0001

Data Index: 350185 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6277. Min Act: -0.0001

Data Index: 11099 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5512. Min Act: -0.0001

Data Index: 781034 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6721. Min Act: -0.0001

Data Index: 870541 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6038. Min Act: -0.0001

Data Index: 152352 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5959. Min Act: -0.0001

Data Index: 158787 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6395. Min Act: -0.0001

Data Index: 383555 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5984. Min Act: -0.0001

Data Index: 380242 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5480. Min Act: -0.0001

Data Index: 850032 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6150. Min Act: -0.0001

Data Index: 892917 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5372. Min Act: -0.0001

Data Index: 446235 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5571. Min Act: -0.0001

Data Index: 1172391 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5551. Min Act: -0.0001

Data Index: 203699 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5389. Min Act: -0.0001

Data Index: 971467 (C4 (Web Text))

Max Activating Token Index: 700