Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1643. Min Act: -0.0000

Data Index: 655782 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1254. Min Act: -0.0000

Data Index: 215154 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1182. Min Act: -0.0000

Data Index: 487286 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1001515 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1116. Min Act: -0.0000

Data Index: 40583 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1206. Min Act: -0.0000

Data Index: 114556 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1045. Min Act: -0.0000

Data Index: 530437 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1128277 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1244678 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1036093 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1142668 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0989. Min Act: -0.0000

Data Index: 51158 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1040. Min Act: -0.0000

Data Index: 300463 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0978. Min Act: -0.0000

Data Index: 591533 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1209221 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0972. Min Act: -0.0000

Data Index: 274731 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1075962 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0912. Min Act: -0.0000

Data Index: 602119 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0916. Min Act: -0.0000

Data Index: 54017 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0950. Min Act: -0.0000

Data Index: 197947 (C4 (Web Text))

Max Activating Token Index: 583