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

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

Neuron 3843 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.3148. Min Act: -0.0001

Data Index: 892271 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.2311. Min Act: -0.0001

Data Index: 653102 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1257. Min Act: -0.0001

Data Index: 236397 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0996. Min Act: -0.0001

Data Index: 96572 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1051. Min Act: -0.0001

Data Index: 582596 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0940. Min Act: -0.0001

Data Index: 118604 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0527. Min Act: -0.0001

Data Index: 764696 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1840. Min Act: -0.0001

Data Index: 937278 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0807. Min Act: -0.0001

Data Index: 1039686 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1137. Min Act: -0.0001

Data Index: 18427 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1807. Min Act: -0.0001

Data Index: 892688 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0970. Min Act: -0.0001

Data Index: 1233545 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0626. Min Act: -0.0001

Data Index: 257392 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0931. Min Act: -0.0001

Data Index: 838106 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.3148. Min Range: -1.3148

Max Act: 0.9053. Min Act: -0.0001

Data Index: 723641 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0170. Min Act: -0.0001

Data Index: 96050 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1060. Min Act: -0.0001

Data Index: 912073 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.0388. Min Act: -0.0001

Data Index: 126507 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.3148. Min Range: -1.3148

Max Act: 1.1325. Min Act: -0.0001

Data Index: 197935 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.3148. Min Range: -1.3148

Max Act: 0.9793. Min Act: -0.0001

Data Index: 531247 (C4 (Web Text))

Max Activating Token Index: 607