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

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

Neuron 4690 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.8700. Min Act: -0.0000

Data Index: 1064614 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.4958. Min Act: -0.0000

Data Index: 500241 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 3.0473. Min Range: -3.0473

Max Act: 3.0473. Min Act: -0.0000

Data Index: 894253 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.6889. Min Act: -0.0000

Data Index: 46723 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.5371. Min Act: -0.0000

Data Index: 849845 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1285504 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.9147. Min Act: -0.0000

Data Index: 1026568 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.2624. Min Act: -0.0000

Data Index: 312506 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.4479. Min Act: -0.0000

Data Index: 533232 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.5425. Min Act: -0.0000

Data Index: 570210 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.7170. Min Act: -0.0000

Data Index: 214425 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.4310. Min Act: -0.0000

Data Index: 1066007 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.2886. Min Act: -0.0000

Data Index: 246034 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.5003. Min Act: -0.0000

Data Index: 519825 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.3920. Min Act: -0.0000

Data Index: 1337668 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.4997. Min Act: -0.0000

Data Index: 1136659 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.3454. Min Act: -0.0000

Data Index: 284188 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 3.0473. Min Range: -3.0473

Max Act: 1.9944. Min Act: -0.0000

Data Index: 954051 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.3159. Min Act: -0.0000

Data Index: 603925 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.0473. Min Range: -3.0473

Max Act: 2.4422. Min Act: -0.0000

Data Index: 1101519 (C4 (Web Text))

Max Activating Token Index: 198