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

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

Neuron 3431 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.9890. Min Act: -0.0000

Data Index: 1350458 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.9022. Min Act: -0.0000

Data Index: 108301 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.5852. Min Act: -0.0000

Data Index: 1304038 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.3552. Min Act: -0.0000

Data Index: 53098 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.3199. Min Act: -0.0000

Data Index: 784199 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.2777. Min Act: -0.0000

Data Index: 515321 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.5804. Min Act: -0.0000

Data Index: 588949 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.2203. Min Act: -0.0000

Data Index: 191470 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.1716. Min Act: -0.0000

Data Index: 1296882 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.0022. Min Act: -0.0000

Data Index: 1045636 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.1566. Min Act: -0.0000

Data Index: 230485 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.1175. Min Act: -0.0000

Data Index: 58891 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 4.9890. Min Range: -4.9890

Max Act: 4.4181. Min Act: -0.0000

Data Index: 911926 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.8044. Min Act: -0.0000

Data Index: 703925 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.8206. Min Act: -0.0000

Data Index: 1283583 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.9356. Min Act: -0.0000

Data Index: 943943 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.6889. Min Act: -0.0000

Data Index: 617709 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.8023. Min Act: -0.0000

Data Index: 376554 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.9686. Min Act: -0.0000

Data Index: 18539 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 4.9890. Min Range: -4.9890

Max Act: 3.9505. Min Act: -0.0000

Data Index: 914467 (C4 (Web Text))

Max Activating Token Index: 544