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

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

Neuron 406 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0000

Data Index: 731919 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1478. Min Act: -0.0000

Data Index: 947733 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1280096 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1183. Min Act: -0.0000

Data Index: 189311 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9971. Min Act: -0.0000

Data Index: 534820 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1324703 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1435157 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9759. Min Act: -0.0000

Data Index: 42359 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9000. Min Act: -0.0000

Data Index: 387328 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8821. Min Act: -0.0000

Data Index: 836621 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1516360 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8444. Min Act: -0.0000

Data Index: 554060 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8358. Min Act: -0.0000

Data Index: 694703 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1422054 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1427068 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1409298 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8121. Min Act: -0.0000

Data Index: 442326 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1434208 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1444972 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7522. Min Act: -0.0000

Data Index: 170574 (C4 (Web Text))

Max Activating Token Index: 270