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

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

Neuron 1273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4676. Min Range: -2.4676

Max Act: 2.4676. Min Act: -0.0000

Data Index: 318465 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 2.4676. Min Range: -2.4676

Max Act: 2.2603. Min Act: -0.0000

Data Index: 246629 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 2.4676. Min Range: -2.4676

Max Act: 2.2321. Min Act: -0.0000

Data Index: 476625 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 2.4676. Min Range: -2.4676

Max Act: 2.2247. Min Act: -0.0000

Data Index: 401752 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 2.4676. Min Range: -2.4676

Max Act: 2.0679. Min Act: -0.0000

Data Index: 1229103 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 2.4676. Min Range: -2.4676

Max Act: 2.0365. Min Act: -0.0000

Data Index: 132530 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.8915. Min Act: -0.0000

Data Index: 930138 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.9828. Min Act: -0.0000

Data Index: 513100 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.8747. Min Act: -0.0000

Data Index: 1108034 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.9571. Min Act: -0.0000

Data Index: 337380 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.8433. Min Act: -0.0000

Data Index: 941711 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.7645. Min Act: -0.0000

Data Index: 869882 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.7680. Min Act: -0.0000

Data Index: 780679 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.7662. Min Act: -0.0000

Data Index: 221811 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.7560. Min Act: -0.0000

Data Index: 872881 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.7533. Min Act: -0.0000

Data Index: 339830 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.8323. Min Act: -0.0000

Data Index: 729298 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.6456. Min Act: -0.0000

Data Index: 202609 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1276505 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 2.4676. Min Range: -2.4676

Max Act: 1.5978. Min Act: -0.0000

Data Index: 170878 (C4 (Web Text))

Max Activating Token Index: 87