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

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

Neuron 3329 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.3671. Min Act: -0.0000

Data Index: 1411217 (Python Code)

Max Activating Token Index: 214

Text #1

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.1654. Min Act: -0.0000

Data Index: 1443930 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0235. Min Act: -0.0000

Data Index: 1369693 (Python Code)

Max Activating Token Index: 445

Text #3

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0125. Min Act: -0.0000

Data Index: 1427185 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 2.3671. Min Range: -2.3671

Max Act: 2.0118. Min Act: -0.0000

Data Index: 1572715 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1444778 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8797. Min Act: -0.0000

Data Index: 1418292 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1498492 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8197. Min Act: -0.0000

Data Index: 1549482 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8336. Min Act: -0.0000

Data Index: 1584160 (Python Code)

Max Activating Token Index: 906

Text #10

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7824. Min Act: -0.0000

Data Index: 1529719 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1538842 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7921. Min Act: -0.0000

Data Index: 1491611 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7820. Min Act: -0.0000

Data Index: 1467701 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1578783 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1378460 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1486650 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7905. Min Act: -0.0000

Data Index: 1521883 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.6426. Min Act: -0.0000

Data Index: 1438205 (Python Code)

Max Activating Token Index: 462

Text #19

Max Range: 2.3671. Min Range: -2.3671

Max Act: 1.7176. Min Act: -0.0000

Data Index: 1466726 (Python Code)

Max Activating Token Index: 969