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

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

Neuron 1111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1018813 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 900933 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0534. Min Act: -0.0002

Data Index: 255326 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1184820 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0556. Min Act: -0.0002

Data Index: 279195 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1337640 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0473. Min Act: -0.0002

Data Index: 919656 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0483. Min Act: -0.0002

Data Index: 897493 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0513. Min Act: -0.0002

Data Index: 106160 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0480. Min Act: -0.0002

Data Index: 878111 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0460. Min Act: -0.0002

Data Index: 840676 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1322643 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0457. Min Act: -0.0002

Data Index: 722507 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1066314 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1256150 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1183478 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1018917 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0399. Min Act: -0.0002

Data Index: 222491 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1196173 (C4 (Web Text))

Max Activating Token Index: 620