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

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

Neuron 4840 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3030. Min Act: -0.0000

Data Index: 986676 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3118. Min Act: -0.0000

Data Index: 677563 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1283147 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3257. Min Act: 0.0000

Data Index: 793644 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2897. Min Act: -0.0000

Data Index: 572057 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2827. Min Act: -0.0000

Data Index: 700449 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2561. Min Act: -0.0000

Data Index: 580960 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2699. Min Act: -0.0000

Data Index: 237533 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2703. Min Act: -0.0000

Data Index: 792305 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2669. Min Act: -0.0000

Data Index: 936511 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2652. Min Act: -0.0000

Data Index: 510814 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1336913 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1219664 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2602. Min Act: -0.0000

Data Index: 982076 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2404. Min Act: -0.0000

Data Index: 790348 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2472. Min Act: -0.0000

Data Index: 104481 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2442. Min Act: -0.0000

Data Index: 14904 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2765. Min Act: -0.0000

Data Index: 206784 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2343. Min Act: -0.0000

Data Index: 779878 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2203. Min Act: -0.0000

Data Index: 117499 (C4 (Web Text))

Max Activating Token Index: 930