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

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

Neuron 5582 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7609. Min Range: -5.7609

Max Act: 5.7609. Min Act: -0.0001

Data Index: 1290239 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 5.7609. Min Range: -5.7609

Max Act: 5.3945. Min Act: -0.0001

Data Index: 782863 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 5.7609. Min Range: -5.7609

Max Act: 5.0998. Min Act: -0.0001

Data Index: 606429 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 5.7609. Min Range: -5.7609

Max Act: 4.6428. Min Act: -0.0001

Data Index: 386000 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 5.7609. Min Range: -5.7609

Max Act: 4.6878. Min Act: -0.0001

Data Index: 692342 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.7609. Min Range: -5.7609

Max Act: 4.6511. Min Act: -0.0001

Data Index: 325561 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 5.7609. Min Range: -5.7609

Max Act: 4.5323. Min Act: -0.0001

Data Index: 757318 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.8376. Min Act: -0.0001

Data Index: 317494 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.7256. Min Act: -0.0001

Data Index: 1195461 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.5846. Min Act: -0.0001

Data Index: 123292 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.5371. Min Act: -0.0001

Data Index: 1078590 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.3970. Min Act: -0.0001

Data Index: 207600 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.2412. Min Act: -0.0001

Data Index: 119024 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.5295. Min Act: -0.0001

Data Index: 101476 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.3505. Min Act: -0.0001

Data Index: 248545 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.1505. Min Act: -0.0001

Data Index: 1022911 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.1040. Min Act: -0.0001

Data Index: 729716 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.1033. Min Act: -0.0001

Data Index: 740048 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.1068. Min Act: -0.0001

Data Index: 525946 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 5.7609. Min Range: -5.7609

Max Act: 3.3893. Min Act: -0.0001

Data Index: 1249542 (C4 (Web Text))

Max Activating Token Index: 672