Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0854. Min Range: -1.0854

Max Act: 1.0854. Min Act: -0.0001

Data Index: 85528 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.9754. Min Act: -0.0001

Data Index: 873094 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1007992 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.8303. Min Act: -0.0001

Data Index: 194906 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7970. Min Act: -0.0001

Data Index: 859502 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.8367. Min Act: -0.0001

Data Index: 26423 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7839. Min Act: -0.0001

Data Index: 1149076 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7662. Min Act: -0.0001

Data Index: 717819 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1192831 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7211. Min Act: -0.0001

Data Index: 291389 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1084110 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7416. Min Act: -0.0001

Data Index: 879349 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7046. Min Act: -0.0001

Data Index: 370623 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7529. Min Act: -0.0001

Data Index: 543795 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7176. Min Act: -0.0001

Data Index: 295775 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1101528 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6970. Min Act: -0.0001

Data Index: 889502 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7479. Min Act: -0.0001

Data Index: 64939 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1079719 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7490. Min Act: -0.0001

Data Index: 594309 (C4 (Web Text))

Max Activating Token Index: 985