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

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

Neuron 1852 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: 2.3736. Min Range: -2.3736

Max Act: 2.3736. Min Act: -0.0000

Data Index: 876683 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 2.3736. Min Range: -2.3736

Max Act: 2.0025. Min Act: -0.0000

Data Index: 1470246 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.6220. Min Act: -0.0000

Data Index: 1198264 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1235991 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.4386. Min Act: -0.0000

Data Index: 443798 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.2692. Min Act: -0.0000

Data Index: 1467581 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1059618 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1491329 (Python Code)

Max Activating Token Index: 427

Text #8

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1346384 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1502972 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0924. Min Act: -0.0000

Data Index: 102624 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.1327. Min Act: -0.0000

Data Index: 569610 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0496. Min Act: -0.0000

Data Index: 782485 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 2.3736. Min Range: -2.3736

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1284295 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1498793 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.1311. Min Act: -0.0000

Data Index: 565542 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1068987 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0398. Min Act: -0.0000

Data Index: 957916 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.3736. Min Range: -2.3736

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1241751 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 2.3736. Min Range: -2.3736

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1171857 (C4 (Web Text))

Max Activating Token Index: 772