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

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

Neuron 2560 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1172864 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1583376 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.4088. Min Act: -0.0000

Data Index: 1499340 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1610357 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1550453 (Python Code)

Max Activating Token Index: 339

Text #5

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1487542 (Python Code)

Max Activating Token Index: 270

Text #6

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1088754 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1089897 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1395655 (Python Code)

Max Activating Token Index: 1001

Text #9

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1503960 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1662. Min Act: -0.0000

Data Index: 814475 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1413662 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1465470 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1521460 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1624029 (Python Code)

Max Activating Token Index: 636

Text #15

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1562752 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1356. Min Act: -0.0000

Data Index: 178538 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1545142 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1586371 (Python Code)

Max Activating Token Index: 677

Text #19

Max Range: 1.5712. Min Range: -1.5712

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1531732 (Python Code)

Max Activating Token Index: 768