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

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

Neuron 5719 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.6443. Min Act: -0.0000

Data Index: 47578 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.6533. Min Act: -0.0000

Data Index: 852850 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1293801 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5845. Min Act: -0.0000

Data Index: 158514 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5386. Min Act: -0.0000

Data Index: 316819 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1327264 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5449. Min Act: -0.0000

Data Index: 891009 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1156415 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5200. Min Act: -0.0000

Data Index: 177741 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5350. Min Act: -0.0000

Data Index: 81620 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1318882 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5244. Min Act: -0.0000

Data Index: 599815 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1152136 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1321667 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5157. Min Act: -0.0000

Data Index: 291444 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5070. Min Act: -0.0000

Data Index: 198334 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4902. Min Act: -0.0000

Data Index: 576796 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1024306 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.4974. Min Act: -0.0000

Data Index: 361162 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.6533. Min Range: -0.6533

Max Act: 0.5140. Min Act: -0.0000

Data Index: 306380 (C4 (Web Text))

Max Activating Token Index: 289