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

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

Neuron 1111 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: 0.6347. Min Range: -0.6347

Max Act: 0.6347. Min Act: -0.0000

Data Index: 858825 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1205777 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1352473 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1221084 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1001927 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4750. Min Act: -0.0000

Data Index: 919633 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4611. Min Act: -0.0000

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1297796 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4519. Min Act: -0.0000

Data Index: 40844 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4451. Min Act: -0.0000

Data Index: 311901 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4363. Min Act: -0.0000

Data Index: 293112 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4332. Min Act: -0.0000

Data Index: 558019 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4451. Min Act: -0.0000

Data Index: 689810 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4136. Min Act: -0.0000

Data Index: 917619 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1112172 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4032. Min Act: -0.0000

Data Index: 526319 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4167. Min Act: -0.0000

Data Index: 880662 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1120977 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1039828 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3926. Min Act: -0.0000

Data Index: 76066 (C4 (Web Text))

Max Activating Token Index: 823