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

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

Neuron 4464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 92092 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7485. Min Act: -0.0000

Data Index: 341017 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6379. Min Act: -0.0000

Data Index: 987899 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1123781 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6453. Min Act: -0.0000

Data Index: 755487 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6215. Min Act: -0.0000

Data Index: 824372 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5913. Min Act: -0.0000

Data Index: 434585 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5880. Min Act: -0.0000

Data Index: 481210 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1167764 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5806. Min Act: -0.0000

Data Index: 176756 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5588. Min Act: -0.0000

Data Index: 219795 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5517. Min Act: -0.0000

Data Index: 401150 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1348380 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5621. Min Act: -0.0000

Data Index: 89968 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5539. Min Act: -0.0000

Data Index: 57972 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1077887 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5267. Min Act: -0.0000

Data Index: 462347 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1267929 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4604. Min Act: -0.0000

Data Index: 831242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5328. Min Act: -0.0000

Data Index: 503407 (C4 (Web Text))

Max Activating Token Index: 672