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

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

Neuron 979 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: 1.5962. Min Range: -1.5962

Max Act: 1.5962. Min Act: -0.0000

Data Index: 171733 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.4603. Min Act: 0.0000

Data Index: 981578 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.5167. Min Act: -0.0000

Data Index: 856803 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1031116 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.3079. Min Act: 0.0000

Data Index: 780232 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1004616 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.3687. Min Act: -0.0000

Data Index: 896829 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.2230. Min Act: -0.0000

Data Index: 792728 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1152473 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1916. Min Act: -0.0000

Data Index: 659562 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1828. Min Act: -0.0000

Data Index: 28543 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1052. Min Act: -0.0000

Data Index: 957174 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1010. Min Act: -0.0000

Data Index: 894486 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1514. Min Act: 0.0000

Data Index: 1281168 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1395. Min Act: -0.0000

Data Index: 548066 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1336876 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1211. Min Act: 0.0000

Data Index: 509059 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1263. Min Act: -0.0000

Data Index: 1153502 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1216. Min Act: -0.0000

Data Index: 541001 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.5962. Min Range: -1.5962

Max Act: 1.1146. Min Act: -0.0000

Data Index: 857306 (C4 (Web Text))

Max Activating Token Index: 254