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

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

Neuron 5779 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1654. Min Range: -3.1654

Max Act: 3.1654. Min Act: -0.0000

Data Index: 180557 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.7232. Min Act: -0.0000

Data Index: 65108 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.6353. Min Act: -0.0000

Data Index: 1084463 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.7246. Min Act: -0.0000

Data Index: 735348 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.7106. Min Act: -0.0000

Data Index: 1321539 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.6422. Min Act: -0.0000

Data Index: 1443422 (Python Code)

Max Activating Token Index: 711

Text #6

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.6414. Min Act: -0.0000

Data Index: 570411 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.7414. Min Act: -0.0000

Data Index: 709499 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.4851. Min Act: -0.0000

Data Index: 805249 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.5806. Min Act: -0.0000

Data Index: 112730 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.4974. Min Act: -0.0000

Data Index: 24506 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.4838. Min Act: -0.0000

Data Index: 1297573 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.3587. Min Act: -0.0000

Data Index: 1267977 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.4693. Min Act: -0.0000

Data Index: 322387 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.6037. Min Act: -0.0000

Data Index: 856455 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.5965. Min Act: -0.0000

Data Index: 1066971 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.3371. Min Act: -0.0000

Data Index: 597478 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.2824. Min Act: -0.0000

Data Index: 1390486 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1193162 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.1654. Min Range: -3.1654

Max Act: 2.4115. Min Act: -0.0000

Data Index: 342997 (C4 (Web Text))

Max Activating Token Index: 57