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

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

Neuron 3794 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: 1.1856. Min Range: -1.1856

Max Act: 1.1337. Min Act: -0.0000

Data Index: 871979 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.1856. Min Range: -1.1856

Max Act: 1.1856. Min Act: -0.0000

Data Index: 867957 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 1.1856. Min Range: -1.1856

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1135989 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.1856. Min Range: -1.1856

Max Act: 1.0241. Min Act: -0.0000

Data Index: 418320 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9164. Min Act: 0.0000

Data Index: 991596 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9823. Min Act: -0.0000

Data Index: 237669 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9141. Min Act: -0.0000

Data Index: 862934 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1323152 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.1856. Min Range: -1.1856

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1219520 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9507. Min Act: -0.0000

Data Index: 602353 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9467. Min Act: -0.0000

Data Index: 379441 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1229845 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9332. Min Act: -0.0000

Data Index: 81715 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1008302 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9171. Min Act: -0.0000

Data Index: 861656 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9272. Min Act: -0.0000

Data Index: 192490 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1160465 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 1.1856. Min Range: -1.1856

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1284366 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.9019. Min Act: -0.0000

Data Index: 103250 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.1856. Min Range: -1.1856

Max Act: 0.8985. Min Act: 0.0000

Data Index: 761058 (C4 (Web Text))

Max Activating Token Index: 35