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

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

Neuron 1903 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2633. Min Range: -1.2633

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1258827 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 1.2633. Min Range: -1.2633

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1118103 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.2633. Min Range: -1.2633

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1027851 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.2633. Min Range: -1.2633

Max Act: 1.0168. Min Act: -0.0000

Data Index: 274253 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7943. Min Act: -0.0000

Data Index: 376089 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7623. Min Act: -0.0000

Data Index: 488866 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7429. Min Act: -0.0000

Data Index: 449098 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1567552 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1470788 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1515451 (Python Code)

Max Activating Token Index: 330

Text #10

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1055520 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.7031. Min Act: -0.0000

Data Index: 147931 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6398. Min Act: -0.0000

Data Index: 868492 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6564. Min Act: -0.0000

Data Index: 915444 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6496. Min Act: -0.0000

Data Index: 841483 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6260. Min Act: -0.0000

Data Index: 179175 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1048926 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1374615 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6260. Min Act: -0.0000

Data Index: 466090 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.2633. Min Range: -1.2633

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1026616 (C4 (Web Text))

Max Activating Token Index: 132