Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.6907. Min Range: -7.6907

Max Act: 7.6907. Min Act: -0.0000

Data Index: 1254953 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.7716. Min Act: -0.0000

Data Index: 470961 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.9593. Min Act: -0.0000

Data Index: 1053502 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.5993. Min Act: -0.0000

Data Index: 466704 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.6335. Min Act: -0.0000

Data Index: 15467 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.7705. Min Act: -0.0000

Data Index: 968386 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.2583. Min Act: -0.0000

Data Index: 1353571 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.4059. Min Act: -0.0000

Data Index: 542590 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.2531. Min Act: -0.0000

Data Index: 771767 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.3396. Min Act: -0.0000

Data Index: 1027031 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.3088. Min Act: -0.0000

Data Index: 212824 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.3143. Min Act: -0.0000

Data Index: 810110 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.1262. Min Act: -0.0000

Data Index: 182774 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 7.6907. Min Range: -7.6907

Max Act: 3.5894. Min Act: -0.0000

Data Index: 1307712 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 7.6907. Min Range: -7.6907

Max Act: 3.6881. Min Act: -0.0000

Data Index: 1063641 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 7.6907. Min Range: -7.6907

Max Act: 3.8263. Min Act: -0.0000

Data Index: 35367 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 7.6907. Min Range: -7.6907

Max Act: 3.8459. Min Act: -0.0000

Data Index: 833553 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 7.6907. Min Range: -7.6907

Max Act: 4.0028. Min Act: -0.0000

Data Index: 474434 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 7.6907. Min Range: -7.6907

Max Act: 3.7324. Min Act: -0.0000

Data Index: 1333793 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 7.6907. Min Range: -7.6907

Max Act: 3.6989. Min Act: -0.0000

Data Index: 364094 (C4 (Web Text))

Max Activating Token Index: 584