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

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

Neuron 5872 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.7257. Min Act: -0.0002

Data Index: 1041949 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.6089. Min Act: -0.0002

Data Index: 824201 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5959. Min Act: -0.0002

Data Index: 563061 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5741. Min Act: -0.0002

Data Index: 83520 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5883. Min Act: -0.0002

Data Index: 608917 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5868. Min Act: -0.0002

Data Index: 278183 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5958. Min Act: -0.0002

Data Index: 360309 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5668. Min Act: -0.0002

Data Index: 1046918 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5631. Min Act: -0.0002

Data Index: 603361 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5367. Min Act: -0.0002

Data Index: 50182 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5737. Min Act: -0.0002

Data Index: 988918 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5298. Min Act: -0.0002

Data Index: 1181794 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5484. Min Act: -0.0002

Data Index: 1310595 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5487. Min Act: -0.0002

Data Index: 389628 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5442. Min Act: -0.0002

Data Index: 761569 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5595. Min Act: -0.0002

Data Index: 706495 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5415. Min Act: -0.0002

Data Index: 947772 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5420. Min Act: -0.0002

Data Index: 785953 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5400. Min Act: -0.0002

Data Index: 38274 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.7257. Min Range: -0.7257

Max Act: 0.5346. Min Act: -0.0002

Data Index: 587238 (C4 (Web Text))

Max Activating Token Index: 32