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

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

Neuron 1614 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0246. Min Range: -2.0246

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1364952 (Python Code)

Max Activating Token Index: 578

Text #1

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1469321 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.8431. Min Act: -0.0000

Data Index: 1403603 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.8450. Min Act: -0.0000

Data Index: 1479212 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1423746 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.7606. Min Act: -0.0000

Data Index: 1601459 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1508341 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1597628 (Python Code)

Max Activating Token Index: 610

Text #8

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1504515 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1495133 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1614969 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1385025 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1446584 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1363438 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.1644. Min Act: -0.0000

Data Index: 1564798 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1512489 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1644251 (Python Code)

Max Activating Token Index: 100

Text #17

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1434009 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 2.0246. Min Range: -2.0246

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1535361 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 2.0246. Min Range: -2.0246

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1565394 (Python Code)

Max Activating Token Index: 287