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

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

Neuron 3624 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.1582. Min Act: -0.0000

Data Index: 438544 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1321581 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0417. Min Act: -0.0000

Data Index: 620738 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0852. Min Act: -0.0000

Data Index: 828727 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1289936 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9692. Min Act: -0.0000

Data Index: 244243 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9321. Min Act: -0.0000

Data Index: 377158 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8900. Min Act: -0.0000

Data Index: 77994 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9390. Min Act: -0.0000

Data Index: 796286 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9206. Min Act: -0.0000

Data Index: 800973 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9155. Min Act: -0.0000

Data Index: 553394 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9204. Min Act: -0.0000

Data Index: 65775 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8829. Min Act: -0.0000

Data Index: 951936 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8952. Min Act: -0.0000

Data Index: 276327 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8747. Min Act: -0.0000

Data Index: 871686 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8402. Min Act: -0.0000

Data Index: 554657 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8924. Min Act: -0.0000

Data Index: 298363 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8481. Min Act: -0.0000

Data Index: 380011 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8504. Min Act: -0.0000

Data Index: 709415 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1337231 (C4 (Web Text))

Max Activating Token Index: 459