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

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

Neuron 672 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: 2.4451. Min Range: -2.4451

Max Act: 2.4451. Min Act: -0.0000

Data Index: 1026347 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 2.4451. Min Range: -2.4451

Max Act: 2.0888. Min Act: -0.0000

Data Index: 509519 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.9315. Min Act: -0.0000

Data Index: 1154844 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.9307. Min Act: -0.0000

Data Index: 960614 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.8442. Min Act: -0.0000

Data Index: 821926 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.9503. Min Act: -0.0000

Data Index: 54570 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7056. Min Act: -0.0000

Data Index: 825282 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.6932. Min Act: -0.0000

Data Index: 287164 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7694. Min Act: -0.0000

Data Index: 1010349 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.8284. Min Act: -0.0000

Data Index: 61224 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.6625. Min Act: -0.0000

Data Index: 96545 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.6462. Min Act: -0.0000

Data Index: 628344 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7396. Min Act: -0.0000

Data Index: 639740 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7220. Min Act: -0.0000

Data Index: 735627 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7138. Min Act: -0.0000

Data Index: 124177 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7904. Min Act: -0.0000

Data Index: 622527 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7222. Min Act: -0.0000

Data Index: 1015574 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7076. Min Act: -0.0000

Data Index: 857318 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7040. Min Act: -0.0000

Data Index: 788617 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 2.4451. Min Range: -2.4451

Max Act: 1.7152. Min Act: -0.0000

Data Index: 456729 (C4 (Web Text))

Max Activating Token Index: 175