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

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

Neuron 1442 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2886. Min Range: -2.2886

Max Act: 2.2502. Min Act: -0.0000

Data Index: 729147 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 2.2886. Min Range: -2.2886

Max Act: 2.1958. Min Act: -0.0000

Data Index: 718898 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 2.2886. Min Range: -2.2886

Max Act: 2.2283. Min Act: -0.0000

Data Index: 450468 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 2.2886. Min Range: -2.2886

Max Act: 2.2886. Min Act: -0.0000

Data Index: 376035 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.8442. Min Act: -0.0000

Data Index: 111486 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.8017. Min Act: -0.0000

Data Index: 335523 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.6916. Min Act: -0.0000

Data Index: 414556 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1434104 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1521504 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1193063 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.0881. Min Act: -0.0000

Data Index: 632382 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.2886. Min Range: -2.2886

Max Act: 0.9923. Min Act: -0.0000

Data Index: 771428 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.0945. Min Act: -0.0000

Data Index: 915069 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.0466. Min Act: -0.0000

Data Index: 809170 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 2.2886. Min Range: -2.2886

Max Act: 0.9692. Min Act: -0.0000

Data Index: 344048 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1186158 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1515243 (Python Code)

Max Activating Token Index: 516

Text #17

Max Range: 2.2886. Min Range: -2.2886

Max Act: 1.0085. Min Act: -0.0000

Data Index: 174080 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 2.2886. Min Range: -2.2886

Max Act: 0.9135. Min Act: 0.0000

Data Index: 669901 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 2.2886. Min Range: -2.2886

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1255846 (C4 (Web Text))

Max Activating Token Index: 183