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

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

Neuron 2340 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.5011. Min Act: -0.0001

Data Index: 1058060 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.4475. Min Act: -0.0001

Data Index: 241013 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.5627. Min Act: -0.0001

Data Index: 1013712 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.2272. Min Act: -0.0001

Data Index: 990901 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.1113. Min Act: -0.0001

Data Index: 1264550 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.1747. Min Act: -0.0001

Data Index: 738163 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0957. Min Act: -0.0001

Data Index: 900674 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.1325. Min Act: -0.0001

Data Index: 557678 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.1355. Min Act: -0.0001

Data Index: 1631783 (Python Code)

Max Activating Token Index: 246

Text #9

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.1572. Min Act: -0.0001

Data Index: 613512 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0514. Min Act: -0.0001

Data Index: 330613 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.1450. Min Act: -0.0001

Data Index: 166451 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0722. Min Act: -0.0001

Data Index: 1283084 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0514. Min Act: -0.0001

Data Index: 697382 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0703. Min Act: -0.0001

Data Index: 242567 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0983. Min Act: -0.0001

Data Index: 105204 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0424. Min Act: -0.0001

Data Index: 145601 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0244. Min Act: -0.0001

Data Index: 940373 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.5627. Min Range: -1.5627

Max Act: 0.9860. Min Act: -0.0001

Data Index: 918543 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 1.5627. Min Range: -1.5627

Max Act: 1.0785. Min Act: -0.0001

Data Index: 725458 (C4 (Web Text))

Max Activating Token Index: 1017