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

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

Neuron 392 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.2073. Min Act: -0.0000

Data Index: 438799 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1988. Min Act: -0.0000

Data Index: 157917 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1947. Min Act: -0.0000

Data Index: 281306 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1903. Min Act: -0.0000

Data Index: 645503 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1282735 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1701. Min Act: -0.0000

Data Index: 305059 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1619. Min Act: -0.0000

Data Index: 857283 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1595. Min Act: -0.0000

Data Index: 239238 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1498. Min Act: -0.0000

Data Index: 720400 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1462. Min Act: -0.0000

Data Index: 276618 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1350691 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1553. Min Act: -0.0000

Data Index: 452896 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1476. Min Act: -0.0000

Data Index: 549130 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1120471 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1180725 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1451. Min Act: -0.0000

Data Index: 65182 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1493. Min Act: -0.0000

Data Index: 996787 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1383. Min Act: -0.0000

Data Index: 463067 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1450. Min Act: -0.0000

Data Index: 339990 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1385. Min Act: -0.0000

Data Index: 370435 (C4 (Web Text))

Max Activating Token Index: 261