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

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

Neuron 4296 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.5292. Min Act: -0.0001

Data Index: 977181 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4591. Min Act: -0.0001

Data Index: 206379 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.5139. Min Act: -0.0001

Data Index: 712551 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4534. Min Act: -0.0001

Data Index: 781946 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4354. Min Act: -0.0001

Data Index: 144242 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1248243 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4552. Min Act: -0.0001

Data Index: 1278995 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3649. Min Act: -0.0001

Data Index: 368773 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4461. Min Act: -0.0001

Data Index: 143772 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4186. Min Act: -0.0001

Data Index: 1187334 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4117. Min Act: -0.0001

Data Index: 862673 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4384. Min Act: -0.0001

Data Index: 1243086 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4082. Min Act: -0.0001

Data Index: 1085318 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4188. Min Act: -0.0001

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4172. Min Act: -0.0001

Data Index: 1233509 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4209. Min Act: -0.0001

Data Index: 889215 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4252. Min Act: -0.0001

Data Index: 878086 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4246. Min Act: -0.0001

Data Index: 794921 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4026. Min Act: -0.0001

Data Index: 53006 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3973. Min Act: -0.0001

Data Index: 1291463 (C4 (Web Text))

Max Activating Token Index: 104