Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1992 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.8382. Min Act: -0.0001

Data Index: 1492944 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1399372 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7776. Min Act: -0.0001

Data Index: 1192223 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7275. Min Act: -0.0001

Data Index: 1605739 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7584. Min Act: -0.0001

Data Index: 364029 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7497. Min Act: -0.0001

Data Index: 1374153 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1638719 (Python Code)

Max Activating Token Index: 333

Text #7

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6957. Min Act: -0.0001

Data Index: 878865 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6851. Min Act: -0.0001

Data Index: 483109 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6664. Min Act: -0.0001

Data Index: 101349 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6191. Min Act: -0.0001

Data Index: 1503931 (Python Code)

Max Activating Token Index: 556

Text #11

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6618. Min Act: -0.0001

Data Index: 76476 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1644657 (Python Code)

Max Activating Token Index: 637

Text #13

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1608154 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6245. Min Act: -0.0001

Data Index: 1415703 (Python Code)

Max Activating Token Index: 661

Text #15

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6557. Min Act: -0.0001

Data Index: 1622823 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.5899. Min Act: -0.0001

Data Index: 1475723 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6248. Min Act: -0.0001

Data Index: 1593784 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6404. Min Act: -0.0001

Data Index: 1606179 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6201. Min Act: -0.0001

Data Index: 1652586 (Python Code)

Max Activating Token Index: 397