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

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

Neuron 3502 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1555026 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.4412. Min Act: -0.0000

Data Index: 1424121 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1628618 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1373702 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1433105 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1577481 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1489618 (Python Code)

Max Activating Token Index: 247

Text #7

Max Range: 1.4831. Min Range: -1.4831

Max Act: 0.9765. Min Act: -0.0000

Data Index: 1360831 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 1.4831. Min Range: -1.4831

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1628440 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1602382 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 1.4831. Min Range: -1.4831

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1369856 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 1.4831. Min Range: -1.4831

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1386759 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1428751 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1567354 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1585319 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1431065 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 1.4831. Min Range: -1.4831

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1464420 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 1.4831. Min Range: -1.4831

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1527557 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1505909 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1573394 (Python Code)

Max Activating Token Index: 586