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

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

Neuron 23 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.8650. Min Act: 0.0001

Data Index: 1624752 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7843. Min Act: 0.0000

Data Index: 1530517 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7581. Min Act: -0.0001

Data Index: 1376259 (Python Code)

Max Activating Token Index: 464

Text #3

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1546438 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1422605 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1450458 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1414791 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1488030 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1361365 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7135. Min Act: 0.0000

Data Index: 1360084 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7133. Min Act: -0.0001

Data Index: 1626855 (Python Code)

Max Activating Token Index: 492

Text #11

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1393828 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1584176 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1555092 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1430910 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1501026 (Python Code)

Max Activating Token Index: 810

Text #16

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6696. Min Act: -0.0001

Data Index: 1488378 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6893. Min Act: -0.0001

Data Index: 1484875 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1551463 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 0.8650. Min Range: -0.8650

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1436249 (Python Code)

Max Activating Token Index: 884