Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.2161. Min Act: -0.0001

Data Index: 523407 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.1348. Min Act: -0.0001

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0551. Min Act: -0.0000

Data Index: 599808 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.1110. Min Act: -0.0001

Data Index: 1475979 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.1571. Min Act: -0.0000

Data Index: 202260 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1140370 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0403. Min Act: -0.0000

Data Index: 173511 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1247011 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1300762 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0568. Min Act: -0.0000

Data Index: 299718 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9070. Min Act: -0.0001

Data Index: 759840 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0579. Min Act: -0.0001

Data Index: 1075573 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0775. Min Act: -0.0001

Data Index: 1590148 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1103004 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9974. Min Act: -0.0000

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0164. Min Act: -0.0000

Data Index: 437413 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.2161. Min Range: -1.2161

Max Act: 1.0126. Min Act: -0.0000

Data Index: 393137 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1343961 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9443. Min Act: -0.0000

Data Index: 425338 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.2161. Min Range: -1.2161

Max Act: 0.9357. Min Act: -0.0000

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 652