Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6306. Min Range: -2.6306

Max Act: 2.6306. Min Act: -0.0000

Data Index: 1643474 (Python Code)

Max Activating Token Index: 415

Text #1

Max Range: 2.6306. Min Range: -2.6306

Max Act: 2.4845. Min Act: -0.0000

Data Index: 1462073 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.6383. Min Act: -0.0000

Data Index: 1514901 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.5119. Min Act: -0.0000

Data Index: 58754 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1423395 (Python Code)

Max Activating Token Index: 777

Text #5

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.5809. Min Act: -0.0000

Data Index: 799407 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1533425 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1595693 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.4481. Min Act: -0.0000

Data Index: 659383 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.2691. Min Act: -0.0000

Data Index: 1490389 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1274533 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1621165 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3596. Min Act: -0.0000

Data Index: 1447161 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3461. Min Act: -0.0000

Data Index: 78794 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1390357 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3301. Min Act: -0.0001

Data Index: 1394583 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3211. Min Act: -0.0000

Data Index: 858225 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.2165. Min Act: -0.0000

Data Index: 7641 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1419093 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 2.6306. Min Range: -2.6306

Max Act: 1.3597. Min Act: -0.0000

Data Index: 1467324 (Python Code)

Max Activating Token Index: 285