Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 905 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4110. Min Act: -0.0003

Data Index: 1585509 (Python Code)

Max Activating Token Index: 335

Text #1

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.4849. Min Act: -0.0003

Data Index: 1396123 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0428. Min Act: -0.0003

Data Index: 1436365 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0177. Min Act: -0.0003

Data Index: 1440492 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.9839. Min Act: -0.0003

Data Index: 1505342 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0689. Min Act: -0.0003

Data Index: 894155 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0202. Min Act: -0.0003

Data Index: 1399848 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.9999. Min Act: -0.0003

Data Index: 1496964 (Python Code)

Max Activating Token Index: 705

Text #8

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8338. Min Act: -0.0003

Data Index: 833631 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.9531. Min Act: -0.0003

Data Index: 1030332 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0015. Min Act: -0.0003

Data Index: 1405962 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.9382. Min Act: -0.0003

Data Index: 1529899 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8631. Min Act: -0.0003

Data Index: 1600390 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8617. Min Act: -0.0003

Data Index: 1386753 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8647. Min Act: -0.0003

Data Index: 1424376 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8851. Min Act: -0.0003

Data Index: 1315933 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8922. Min Act: -0.0003

Data Index: 919268 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8649. Min Act: -0.0003

Data Index: 1101520 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.7254. Min Act: -0.0003

Data Index: 1101146 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 1.4849. Min Range: -1.4849

Max Act: 0.8520. Min Act: -0.0003

Data Index: 76547 (C4 (Web Text))

Max Activating Token Index: 163