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

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

Neuron 2140 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0529. Min Range: -5.0529

Max Act: 5.0529. Min Act: -0.0000

Data Index: 162047 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.7927. Min Act: -0.0000

Data Index: 1338526 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.7039. Min Act: -0.0000

Data Index: 1251073 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.6823. Min Act: -0.0000

Data Index: 889493 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.2782. Min Act: -0.0000

Data Index: 126361 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0847. Min Act: -0.0000

Data Index: 879583 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0123. Min Act: -0.0000

Data Index: 1000188 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.8015. Min Act: -0.0000

Data Index: 1223545 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0998. Min Act: -0.0000

Data Index: 1005655 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.6955. Min Act: -0.0000

Data Index: 1028347 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.5441. Min Act: -0.0000

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.3058. Min Act: -0.0000

Data Index: 487812 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.4067. Min Act: -0.0000

Data Index: 849349 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.3328. Min Act: -0.0000

Data Index: 1150209 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.4992. Min Act: -0.0000

Data Index: 757112 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.3379. Min Act: -0.0000

Data Index: 966006 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.6287. Min Act: -0.0000

Data Index: 290178 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.2317. Min Act: -0.0000

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.1934. Min Act: -0.0000

Data Index: 933217 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.3575. Min Act: -0.0000

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 433