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

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

Neuron 3998 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: 1.7029. Min Range: -1.7029

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1218948 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.5992. Min Act: -0.0000

Data Index: 774016 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.3224. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.2401. Min Act: -0.0000

Data Index: 776837 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.2350. Min Act: -0.0000

Data Index: 253429 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1018401 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1231306 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.1240. Min Act: -0.0000

Data Index: 559461 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1039562 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.1542. Min Act: -0.0000

Data Index: 663482 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0984. Min Act: -0.0000

Data Index: 885685 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0777. Min Act: -0.0000

Data Index: 797603 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0396. Min Act: -0.0000

Data Index: 487738 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0589. Min Act: -0.0000

Data Index: 824995 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0570. Min Act: -0.0000

Data Index: 506482 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0318. Min Act: -0.0000

Data Index: 753728 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0013. Min Act: -0.0000

Data Index: 314712 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.7029. Min Range: -1.7029

Max Act: 0.9971. Min Act: -0.0000

Data Index: 941929 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.7029. Min Range: -1.7029

Max Act: 1.0233. Min Act: -0.0000

Data Index: 906472 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.7029. Min Range: -1.7029

Max Act: 0.9830. Min Act: -0.0000

Data Index: 154301 (C4 (Web Text))

Max Activating Token Index: 106