Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.4883. Min Act: 0.0000

Data Index: 523613 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.3635. Min Act: -0.0000

Data Index: 256724 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.3282. Min Act: -0.0000

Data Index: 886177 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.3898. Min Act: 0.0001

Data Index: 353706 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2709. Min Act: -0.0000

Data Index: 299749 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2277. Min Act: -0.0000

Data Index: 80184 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2464. Min Act: -0.0000

Data Index: 912532 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1017318 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1751. Min Act: -0.0000

Data Index: 457256 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1631. Min Act: -0.0000

Data Index: 700202 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1206225 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1198352 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1143333 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1780. Min Act: -0.0000

Data Index: 158063 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1102647 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1458. Min Act: -0.0000

Data Index: 109063 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1243. Min Act: -0.0000

Data Index: 650350 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0849. Min Act: -0.0000

Data Index: 422985 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0344. Min Act: 0.0000

Data Index: 1289792 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0468. Min Act: -0.0000

Data Index: 695863 (C4 (Web Text))

Max Activating Token Index: 517