Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1587 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4204. Min Act: -0.0003

Data Index: 1534546 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3371. Min Act: -0.0003

Data Index: 1562285 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3449. Min Act: -0.0003

Data Index: 1579230 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3210. Min Act: -0.0003

Data Index: 1392460 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3157. Min Act: -0.0003

Data Index: 1536662 (Python Code)

Max Activating Token Index: 677

Text #5

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3077. Min Act: -0.0003

Data Index: 1470373 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2986. Min Act: -0.0003

Data Index: 1525919 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2921. Min Act: -0.0003

Data Index: 1409578 (Python Code)

Max Activating Token Index: 486

Text #8

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2864. Min Act: -0.0003

Data Index: 1634117 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3026. Min Act: -0.0003

Data Index: 1454002 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2888. Min Act: -0.0003

Data Index: 1430806 (Python Code)

Max Activating Token Index: 809

Text #11

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2842. Min Act: -0.0003

Data Index: 1598476 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2896. Min Act: -0.0003

Data Index: 1528957 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2708. Min Act: -0.0003

Data Index: 1438919 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2568. Min Act: -0.0003

Data Index: 1394836 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2600. Min Act: -0.0003

Data Index: 1530048 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2498. Min Act: -0.0003

Data Index: 1407707 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2653. Min Act: -0.0003

Data Index: 1561682 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2554. Min Act: -0.0003

Data Index: 1436692 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2558. Min Act: -0.0003

Data Index: 1580083 (Python Code)

Max Activating Token Index: 943