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

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

Neuron 1344 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1538. Min Range: -3.1538

Max Act: 3.1538. Min Act: -0.0000

Data Index: 429154 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.4305. Min Act: -0.0000

Data Index: 1373635 (Python Code)

Max Activating Token Index: 756

Text #2

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.2216. Min Act: -0.0000

Data Index: 1524033 (Python Code)

Max Activating Token Index: 514

Text #3

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.1873. Min Act: -0.0000

Data Index: 970185 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1531937 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.0264. Min Act: -0.0000

Data Index: 1234651 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.1406. Min Act: -0.0000

Data Index: 219517 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.0608. Min Act: -0.0000

Data Index: 349074 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.0549. Min Act: -0.0000

Data Index: 1220840 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.1444. Min Act: -0.0000

Data Index: 535093 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.9953. Min Act: -0.0000

Data Index: 1164060 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.8815. Min Act: -0.0000

Data Index: 1394687 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 3.1538. Min Range: -3.1538

Max Act: 2.0627. Min Act: -0.0000

Data Index: 1369831 (Python Code)

Max Activating Token Index: 534

Text #13

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.9202. Min Act: -0.0000

Data Index: 283615 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.9191. Min Act: -0.0000

Data Index: 1489355 (Python Code)

Max Activating Token Index: 741

Text #15

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.7666. Min Act: -0.0000

Data Index: 910499 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.8704. Min Act: -0.0000

Data Index: 296762 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.8292. Min Act: -0.0000

Data Index: 1372810 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.9435. Min Act: -0.0000

Data Index: 1086765 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 3.1538. Min Range: -3.1538

Max Act: 1.8318. Min Act: -0.0000

Data Index: 582409 (C4 (Web Text))

Max Activating Token Index: 275