Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1529 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1023376 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2134. Min Act: -0.0001

Data Index: 36965 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1105740 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1981. Min Act: -0.0001

Data Index: 323447 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1948. Min Act: -0.0001

Data Index: 121790 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1884. Min Act: -0.0001

Data Index: 36713 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1882. Min Act: -0.0001

Data Index: 325208 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1232398 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1838. Min Act: -0.0001

Data Index: 295002 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1207544 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1827. Min Act: -0.0001

Data Index: 969096 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1689. Min Act: -0.0000

Data Index: 99621 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1284184 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1834. Min Act: -0.0000

Data Index: 518415 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1825. Min Act: -0.0001

Data Index: 521730 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1163277 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1153237 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1198312 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1328587 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1153723 (C4 (Web Text))

Max Activating Token Index: 792