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

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

Neuron 140 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5403. Min Act: -0.0000

Data Index: 291797 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1137939 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4487. Min Act: -0.0000

Data Index: 189750 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4870. Min Act: -0.0000

Data Index: 900471 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1042011 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3692. Min Act: -0.0000

Data Index: 543877 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1267487 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3866. Min Act: -0.0000

Data Index: 181648 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4262. Min Act: 0.0000

Data Index: 1571348 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4308. Min Act: -0.0000

Data Index: 144832 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3684. Min Act: -0.0000

Data Index: 543549 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1555456 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3995. Min Act: -0.0000

Data Index: 818260 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1581537 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3727. Min Act: -0.0000

Data Index: 546970 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1481834 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3816. Min Act: -0.0000

Data Index: 2354 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1565675 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1167017 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1034157 (C4 (Web Text))

Max Activating Token Index: 570