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

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

Neuron 95 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1400500 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1468081 (Python Code)

Max Activating Token Index: 528

Text #2

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1603494 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1652708 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1617743 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1626000 (Python Code)

Max Activating Token Index: 418

Text #6

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1387472 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1511617 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1424650 (Python Code)

Max Activating Token Index: 654

Text #9

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1427756 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1437214 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 1.4496. Min Range: -1.4496

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1423488 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1603044 (Python Code)

Max Activating Token Index: 572

Text #13

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1603965 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1636186 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1461318 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1549386 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1555160 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1408139 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1432291 (Python Code)

Max Activating Token Index: 362