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

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

Neuron 3240 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: 2.4400. Min Range: -2.4400

Max Act: 2.4400. Min Act: -0.0000

Data Index: 1648783 (Python Code)

Max Activating Token Index: 440

Text #1

Max Range: 2.4400. Min Range: -2.4400

Max Act: 2.1252. Min Act: -0.0000

Data Index: 1592937 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 2.4400. Min Range: -2.4400

Max Act: 2.1360. Min Act: -0.0000

Data Index: 1498724 (Python Code)

Max Activating Token Index: 830

Text #3

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.9762. Min Act: -0.0000

Data Index: 1390164 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.9440. Min Act: -0.0000

Data Index: 1479311 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 2.4400. Min Range: -2.4400

Max Act: 2.0065. Min Act: 0.0000

Data Index: 1507316 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.9235. Min Act: 0.0002

Data Index: 1648212 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.9230. Min Act: 0.0000

Data Index: 1541134 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.9109. Min Act: -0.0000

Data Index: 72917 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.8738. Min Act: 0.0000

Data Index: 1588814 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.7833. Min Act: -0.0000

Data Index: 1572325 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.8354. Min Act: -0.0000

Data Index: 1526089 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1533597 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.7051. Min Act: -0.0000

Data Index: 1622528 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1459786 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1598461 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1444167 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.7137. Min Act: 0.0000

Data Index: 1472125 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1637871 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 2.4400. Min Range: -2.4400

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1592171 (Python Code)

Max Activating Token Index: 416