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

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

Neuron 1473 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2774. Min Range: -4.2774

Max Act: 4.0197. Min Act: -0.0001

Data Index: 1480012 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 4.2774. Min Range: -4.2774

Max Act: 4.2774. Min Act: -0.0001

Data Index: 1430834 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 4.2774. Min Range: -4.2774

Max Act: 4.2360. Min Act: -0.0001

Data Index: 1473184 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.7016. Min Act: -0.0001

Data Index: 1529231 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.6299. Min Act: -0.0001

Data Index: 1437153 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.6260. Min Act: -0.0001

Data Index: 1500736 (Python Code)

Max Activating Token Index: 694

Text #6

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.6903. Min Act: -0.0001

Data Index: 1599801 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.8280. Min Act: -0.0001

Data Index: 1474568 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.5523. Min Act: -0.0001

Data Index: 1619320 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.3953. Min Act: -0.0001

Data Index: 1521076 (Python Code)

Max Activating Token Index: 815

Text #10

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.5469. Min Act: -0.0001

Data Index: 1427179 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.5093. Min Act: -0.0001

Data Index: 1399050 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.4161. Min Act: -0.0001

Data Index: 1456422 (Python Code)

Max Activating Token Index: 395

Text #13

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.3524. Min Act: -0.0001

Data Index: 1586688 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.1888. Min Act: -0.0000

Data Index: 1463652 (Python Code)

Max Activating Token Index: 491

Text #15

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.1186. Min Act: -0.0001

Data Index: 1492431 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.0874. Min Act: -0.0001

Data Index: 1542609 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.2196. Min Act: -0.0001

Data Index: 1534927 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.3478. Min Act: -0.0001

Data Index: 1607326 (Python Code)

Max Activating Token Index: 782

Text #19

Max Range: 4.2774. Min Range: -4.2774

Max Act: 3.1791. Min Act: -0.0001

Data Index: 1582182 (Python Code)

Max Activating Token Index: 64