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

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

Neuron 4499 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: 5.4908. Min Range: -5.4908

Max Act: 5.4908. Min Act: -0.0000

Data Index: 343155 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.7269. Min Act: -0.0000

Data Index: 62294 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 5.4908. Min Range: -5.4908

Max Act: 4.1411. Min Act: -0.0000

Data Index: 94608 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.9326. Min Act: -0.0000

Data Index: 95463 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.8413. Min Act: -0.0000

Data Index: 32411 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.7754. Min Act: -0.0000

Data Index: 864217 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.7686. Min Act: -0.0000

Data Index: 922840 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.5684. Min Act: -0.0000

Data Index: 422914 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 5.4908. Min Range: -5.4908

Max Act: 4.0233. Min Act: -0.0000

Data Index: 809274 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.6695. Min Act: -0.0000

Data Index: 80965 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.7530. Min Act: -0.0000

Data Index: 919077 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.4619. Min Act: -0.0000

Data Index: 64142 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.2415. Min Act: -0.0000

Data Index: 1100809 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.3853. Min Act: -0.0000

Data Index: 917937 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.0300. Min Act: -0.0000

Data Index: 1194156 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.0876. Min Act: -0.0000

Data Index: 755861 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 5.4908. Min Range: -5.4908

Max Act: 2.9966. Min Act: -0.0000

Data Index: 835616 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 5.4908. Min Range: -5.4908

Max Act: 2.8488. Min Act: -0.0000

Data Index: 490877 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 5.4908. Min Range: -5.4908

Max Act: 3.3301. Min Act: -0.0000

Data Index: 1006440 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 5.4908. Min Range: -5.4908

Max Act: 2.6934. Min Act: -0.0000

Data Index: 35832 (C4 (Web Text))

Max Activating Token Index: 29