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

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

Neuron 1446 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: 0.4513. Min Range: -0.4513

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1107670 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4513. Min Act: -0.0000

Data Index: 320722 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1417267 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1408095 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1360613 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1406407 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1550620 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4285. Min Act: -0.0001

Data Index: 1260784 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1447071 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1607525 (Python Code)

Max Activating Token Index: 120

Text #10

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1534265 (Python Code)

Max Activating Token Index: 219

Text #11

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1577082 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1381347 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4264. Min Act: -0.0000

Data Index: 287469 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1482918 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1488948 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1589315 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1555368 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1593473 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1002642 (C4 (Web Text))

Max Activating Token Index: 678