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

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

Neuron 1289 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: 3.6015. Min Range: -3.6015

Max Act: 3.6015. Min Act: -0.0001

Data Index: 451531 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 3.6015. Min Range: -3.6015

Max Act: 3.5433. Min Act: -0.0001

Data Index: 896219 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 3.6015. Min Range: -3.6015

Max Act: 3.5417. Min Act: -0.0001

Data Index: 556477 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 3.6015. Min Range: -3.6015

Max Act: 3.1802. Min Act: -0.0000

Data Index: 1004909 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 3.6015. Min Range: -3.6015

Max Act: 3.1302. Min Act: -0.0000

Data Index: 85144 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 3.6015. Min Range: -3.6015

Max Act: 3.0208. Min Act: -0.0000

Data Index: 967944 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.8625. Min Act: -0.0001

Data Index: 938174 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.8592. Min Act: -0.0001

Data Index: 1190292 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.8258. Min Act: -0.0000

Data Index: 1159999 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.8873. Min Act: -0.0000

Data Index: 198122 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.7622. Min Act: -0.0000

Data Index: 1154999 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.7067. Min Act: -0.0000

Data Index: 557670 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.8158. Min Act: -0.0001

Data Index: 726728 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.6816. Min Act: -0.0000

Data Index: 1340423 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.6700. Min Act: -0.0000

Data Index: 303822 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.4602. Min Act: -0.0000

Data Index: 696529 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.4559. Min Act: -0.0000

Data Index: 900035 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.4621. Min Act: -0.0001

Data Index: 699873 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.2064. Min Act: -0.0001

Data Index: 687339 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.6015. Min Range: -3.6015

Max Act: 2.5767. Min Act: -0.0000

Data Index: 595529 (C4 (Web Text))

Max Activating Token Index: 172