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

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

Neuron 1497 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.2061. Min Act: -0.0001

Data Index: 356686 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.2391. Min Act: -0.0001

Data Index: 157711 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.2607. Min Act: -0.0001

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.2711. Min Act: -0.0001

Data Index: 184785 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.2644. Min Act: -0.0000

Data Index: 400273 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1443. Min Act: -0.0001

Data Index: 22738 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1295. Min Act: -0.0001

Data Index: 506684 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0819. Min Act: -0.0001

Data Index: 63740 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0868. Min Act: -0.0001

Data Index: 379973 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1510. Min Act: -0.0001

Data Index: 588720 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1184. Min Act: -0.0001

Data Index: 364464 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1374. Min Act: -0.0001

Data Index: 605960 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0918. Min Act: -0.0001

Data Index: 1007959 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0615. Min Act: -0.0001

Data Index: 619813 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1268. Min Act: -0.0001

Data Index: 1202438 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0975. Min Act: -0.0001

Data Index: 1248216 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1936. Min Act: -0.0001

Data Index: 1029478 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1105058 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.0118. Min Act: -0.0001

Data Index: 929571 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.2711. Min Range: -1.2711

Max Act: 1.1428. Min Act: -0.0001

Data Index: 1021134 (C4 (Web Text))

Max Activating Token Index: 841