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

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

Neuron 1003 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: 1.1830. Min Range: -1.1830

Max Act: 1.1830. Min Act: -0.0001

Data Index: 991434 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.1830. Min Range: -1.1830

Max Act: 1.0632. Min Act: -0.0001

Data Index: 1263971 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8749. Min Act: -0.0001

Data Index: 872143 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9571. Min Act: -0.0001

Data Index: 634168 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9737. Min Act: -0.0001

Data Index: 1652238 (Python Code)

Max Activating Token Index: 160

Text #5

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9554. Min Act: -0.0000

Data Index: 258503 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9829. Min Act: -0.0001

Data Index: 733003 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.1830. Min Range: -1.1830

Max Act: 1.0017. Min Act: -0.0000

Data Index: 494792 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9290. Min Act: -0.0000

Data Index: 42730 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1056654 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1363321 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1252297 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.9133. Min Act: -0.0001

Data Index: 1530258 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8306. Min Act: -0.0001

Data Index: 407118 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1557992 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.7965. Min Act: -0.0001

Data Index: 113202 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.6984. Min Act: -0.0001

Data Index: 570827 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8019. Min Act: -0.0000

Data Index: 62403 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.6965. Min Act: -0.0001

Data Index: 1126931 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 1.1830. Min Range: -1.1830

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1044822 (C4 (Web Text))

Max Activating Token Index: 975