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

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

Neuron 2058 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: 1.2607. Min Range: -1.2607

Max Act: 1.1979. Min Act: -0.0001

Data Index: 1651583 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1672. Min Act: -0.0001

Data Index: 317901 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.2607. Min Act: -0.0001

Data Index: 897361 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.2119. Min Act: -0.0001

Data Index: 1257720 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1471. Min Act: -0.0001

Data Index: 314347 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0949. Min Act: -0.0001

Data Index: 167119 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1615. Min Act: -0.0001

Data Index: 339237 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9658. Min Act: -0.0001

Data Index: 740836 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1408. Min Act: -0.0001

Data Index: 701389 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9513. Min Act: -0.0001

Data Index: 641490 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0735. Min Act: -0.0001

Data Index: 567101 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1417. Min Act: -0.0001

Data Index: 1121631 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1659. Min Act: -0.0001

Data Index: 289551 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0914. Min Act: -0.0001

Data Index: 51644 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1861. Min Act: -0.0001

Data Index: 584646 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9797. Min Act: -0.0001

Data Index: 181623 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0797. Min Act: -0.0001

Data Index: 856412 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1037. Min Act: -0.0001

Data Index: 580498 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1401220 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9324. Min Act: -0.0001

Data Index: 879781 (C4 (Web Text))

Max Activating Token Index: 913