Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 283 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0497. Min Act: -0.0001

Data Index: 51174 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1195945 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1049310 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0472. Min Act: -0.0001

Data Index: 246180 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1288881 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1227736 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0447. Min Act: -0.0001

Data Index: 377484 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0459. Min Act: -0.0001

Data Index: 107075 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0429. Min Act: -0.0001

Data Index: 420994 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0424. Min Act: -0.0001

Data Index: 505867 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1039748 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0441. Min Act: -0.0001

Data Index: 616161 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0454. Min Act: -0.0001

Data Index: 584110 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0438. Min Act: -0.0001

Data Index: 76749 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0449. Min Act: -0.0001

Data Index: 137200 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0430. Min Act: -0.0001

Data Index: 142154 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1285234 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0404. Min Act: -0.0001

Data Index: 294405 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1173529 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0426. Min Act: -0.0001

Data Index: 181798 (C4 (Web Text))

Max Activating Token Index: 18