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

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

Neuron 3216 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.6400. Min Act: -0.0000

Data Index: 1474385 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1364625 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1540385 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1576251 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1398788 (Python Code)

Max Activating Token Index: 827

Text #5

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1371327 (Python Code)

Max Activating Token Index: 572

Text #6

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1579469 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 1.6400. Min Range: -1.6400

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1623182 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1549325 (Python Code)

Max Activating Token Index: 882

Text #9

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1518595 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1531655 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1444576 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1445668 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1473502 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1563252 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1583365 (Python Code)

Max Activating Token Index: 602

Text #16

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1558352 (Python Code)

Max Activating Token Index: 683

Text #17

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1592566 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1505857 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 1.6400. Min Range: -1.6400

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1475086 (Python Code)

Max Activating Token Index: 437