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

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

Neuron 37 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.2185. Min Act: -0.0001

Data Index: 729572 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1830. Min Act: -0.0001

Data Index: 191102 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1627. Min Act: -0.0001

Data Index: 598699 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1681. Min Act: -0.0001

Data Index: 50167 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1589. Min Act: -0.0001

Data Index: 556157 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1317625 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1349432 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1228946 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1538. Min Act: -0.0001

Data Index: 287428 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1017214 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1501. Min Act: -0.0001

Data Index: 155767 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1119175 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1520. Min Act: -0.0000

Data Index: 967942 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1085314 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1429. Min Act: -0.0001

Data Index: 743702 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1074603 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1476. Min Act: -0.0001

Data Index: 731124 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1066721 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1163651 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1438. Min Act: -0.0001

Data Index: 594732 (C4 (Web Text))

Max Activating Token Index: 778