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

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

Neuron 5621 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.5375. Min Act: -0.0001

Data Index: 1481739 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.5429. Min Act: -0.0001

Data Index: 1502506 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1094901 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3721. Min Act: -0.0001

Data Index: 1583175 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3890. Min Act: -0.0001

Data Index: 1483346 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3843. Min Act: -0.0000

Data Index: 1373584 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3343. Min Act: -0.0000

Data Index: 1402294 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3343. Min Act: -0.0001

Data Index: 1625878 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1461493 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3223. Min Act: -0.0001

Data Index: 1602163 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2645. Min Act: -0.0001

Data Index: 1560105 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3043. Min Act: -0.0001

Data Index: 1518312 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2987. Min Act: -0.0001

Data Index: 1492659 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1403177 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1518624 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2261. Min Act: -0.0000

Data Index: 869921 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1633811 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1381898 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3542. Min Act: -0.0001

Data Index: 1635907 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 1.5429. Min Range: -1.5429

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1459229 (Python Code)

Max Activating Token Index: 340