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

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

Neuron 362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1653365 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1111079 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9563. Min Act: -0.0000

Data Index: 6355 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8914. Min Act: -0.0000

Data Index: 708177 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.0065. Min Act: -0.0001

Data Index: 1475572 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1578223 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8701. Min Act: -0.0001

Data Index: 1113481 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1372481 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1379160 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8066. Min Act: -0.0000

Data Index: 184803 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1594261 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8290. Min Act: -0.0000

Data Index: 974391 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1558302 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7905. Min Act: -0.0000

Data Index: 748881 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1265402 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1510574 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1511230 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1591545 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8185. Min Act: -0.0001

Data Index: 1501110 (Python Code)

Max Activating Token Index: 522

Text #19

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1618969 (Python Code)

Max Activating Token Index: 674