Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4149 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1572714 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3083. Min Act: 0.0000

Data Index: 63724 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1972. Min Act: -0.0000

Data Index: 1627449 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1581297 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1640446 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1610426 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1635382 (Python Code)

Max Activating Token Index: 71

Text #7

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.0692. Min Act: -0.0000

Data Index: 646682 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9350. Min Act: -0.0000

Data Index: 893585 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9465. Min Act: -0.0000

Data Index: 757968 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9397. Min Act: 0.0000

Data Index: 1511226 (Python Code)

Max Activating Token Index: 344

Text #11

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9143. Min Act: -0.0000

Data Index: 522923 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1534255 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9077. Min Act: 0.0000

Data Index: 1515022 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1551357 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1461255 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1570170 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1531712 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1625332 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 1.4500. Min Range: -1.4500

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1545393 (Python Code)

Max Activating Token Index: 240