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

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

Neuron 5239 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1385065 (Python Code)

Max Activating Token Index: 643

Text #1

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.1033. Min Act: -0.0000

Data Index: 277981 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.0255. Min Act: -0.0000

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.0202. Min Act: 0.0001

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1583073 (Python Code)

Max Activating Token Index: 226

Text #5

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.0072. Min Act: 0.0000

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.0055. Min Act: 0.0000

Data Index: 172620 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.9655. Min Act: 0.0001

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.3000. Min Range: -1.3000

Max Act: 1.0017. Min Act: -0.0000

Data Index: 833342 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1561214 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1504878 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1504337 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1460662 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1532329 (Python Code)

Max Activating Token Index: 373

Text #14

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8649. Min Act: 0.0001

Data Index: 699784 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8729. Min Act: 0.0000

Data Index: 1472078 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1579984 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8512. Min Act: -0.0000

Data Index: 958805 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.8233. Min Act: -0.0000

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 1.3000. Min Range: -1.3000

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1477993 (Python Code)

Max Activating Token Index: 321