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

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

Neuron 5262 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0001

Data Index: 411086 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0221. Min Act: -0.0001

Data Index: 75313 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0213. Min Act: -0.0001

Data Index: 38840 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0211. Min Act: -0.0001

Data Index: 262084 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1626942 (Python Code)

Max Activating Token Index: 197

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1041501 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0206. Min Act: -0.0001

Data Index: 598289 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0202. Min Act: -0.0001

Data Index: 23295 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1075047 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0001

Data Index: 108375 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0001

Data Index: 568207 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0199. Min Act: -0.0001

Data Index: 341292 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1652388 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0201. Min Act: -0.0001

Data Index: 462622 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1088260 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0197. Min Act: -0.0001

Data Index: 737111 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1053940 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0198. Min Act: -0.0001

Data Index: 8105 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0197. Min Act: -0.0001

Data Index: 479481 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0198. Min Act: -0.0001

Data Index: 278063 (C4 (Web Text))

Max Activating Token Index: 548