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

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

Neuron 3605 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: 1.4026. Min Range: -1.4026

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1469339 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0473. Min Act: 0.0000

Data Index: 1520516 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 1.4026. Min Range: -1.4026

Max Act: 1.0003. Min Act: 0.0000

Data Index: 1434464 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.9554. Min Act: 0.0000

Data Index: 1640034 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1414642 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8981. Min Act: 0.0000

Data Index: 1596411 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.9541. Min Act: 0.0000

Data Index: 1495855 (Python Code)

Max Activating Token Index: 24

Text #7

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8533. Min Act: 0.0000

Data Index: 1382342 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8384. Min Act: 0.0000

Data Index: 1563670 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1596959 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8221. Min Act: 0.0000

Data Index: 1376232 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1589329 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8015. Min Act: -0.0001

Data Index: 785039 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.8304. Min Act: 0.0000

Data Index: 1443758 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7742. Min Act: 0.0000

Data Index: 1396726 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7756. Min Act: 0.0000

Data Index: 1362240 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7924. Min Act: 0.0000

Data Index: 1529338 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7672. Min Act: 0.0000

Data Index: 1365245 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7601. Min Act: 0.0000

Data Index: 1361838 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 1.4026. Min Range: -1.4026

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1638015 (Python Code)

Max Activating Token Index: 19