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

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

Neuron 722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.7542. Min Act: -0.0000

Data Index: 432746 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.6515. Min Act: -0.0000

Data Index: 383601 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.4920. Min Act: -0.0001

Data Index: 230880 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.2483. Min Act: -0.0001

Data Index: 779941 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.1859. Min Act: -0.0001

Data Index: 879141 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.8883. Min Act: -0.0000

Data Index: 1057296 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.1801. Min Act: -0.0000

Data Index: 1240805 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.6144. Min Act: -0.0000

Data Index: 786763 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.8606. Min Act: -0.0001

Data Index: 285701 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.0271. Min Act: -0.0001

Data Index: 839594 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.9735. Min Act: -0.0001

Data Index: 142775 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.1141. Min Act: -0.0001

Data Index: 461641 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.9625. Min Act: -0.0001

Data Index: 966325 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.0917. Min Act: -0.0001

Data Index: 235741 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.6303. Min Act: -0.0001

Data Index: 78548 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.0730. Min Act: -0.0001

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.0688. Min Act: -0.0001

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 4.7542. Min Range: -4.7542

Max Act: 4.0472. Min Act: -0.0000

Data Index: 128308 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.8563. Min Act: -0.0001

Data Index: 115501 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 4.7542. Min Range: -4.7542

Max Act: 3.8016. Min Act: -0.0001

Data Index: 816305 (C4 (Web Text))

Max Activating Token Index: 416