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

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

Neuron 5839 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: 1.3568. Min Range: -1.3568

Max Act: 1.3568. Min Act: 0.0000

Data Index: 1385017 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 1.3568. Min Range: -1.3568

Max Act: 1.2362. Min Act: 0.0000

Data Index: 1539103 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1613257 (Python Code)

Max Activating Token Index: 339

Text #3

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1578626 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 1.3568. Min Range: -1.3568

Max Act: 1.0195. Min Act: 0.0000

Data Index: 1494944 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.9434. Min Act: 0.0001

Data Index: 1609198 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1363810 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.9802. Min Act: 0.0000

Data Index: 1485085 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1256672 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1361839 (Python Code)

Max Activating Token Index: 783

Text #10

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1564670 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8427. Min Act: 0.0001

Data Index: 1472941 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8276. Min Act: -0.0000

Data Index: 455363 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1237984 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1487428 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8776. Min Act: 0.0001

Data Index: 698086 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.7809. Min Act: 0.0001

Data Index: 1417035 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1496822 (Python Code)

Max Activating Token Index: 285

Text #18

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.7708. Min Act: 0.0000

Data Index: 1382996 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 1.3568. Min Range: -1.3568

Max Act: 0.7578. Min Act: 0.0001

Data Index: 1157022 (C4 (Web Text))

Max Activating Token Index: 500