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

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

Neuron 3308 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: 0.3430. Min Range: -0.3430

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1488492 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3254. Min Act: -0.0001

Data Index: 849760 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3249. Min Act: 0.0000

Data Index: 1416708 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3134. Min Act: 0.0000

Data Index: 1541660 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3240. Min Act: 0.0000

Data Index: 1495457 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3183. Min Act: 0.0000

Data Index: 1427267 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1595072 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3155. Min Act: 0.0000

Data Index: 1375801 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3002. Min Act: 0.0000

Data Index: 1561762 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2902. Min Act: -0.0001

Data Index: 121467 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2873. Min Act: 0.0000

Data Index: 1398186 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2958. Min Act: 0.0000

Data Index: 1604985 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1641435 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2704. Min Act: -0.0001

Data Index: 591479 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2456. Min Act: -0.0001

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1592306 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1544491 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2805. Min Act: 0.0000

Data Index: 1590479 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2706. Min Act: 0.0000

Data Index: 1541871 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2606. Min Act: 0.0000

Data Index: 1555540 (Python Code)

Max Activating Token Index: 22