Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 72 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0003

Data Index: 598165 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0479. Min Act: -0.0003

Data Index: 383923 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0464. Min Act: -0.0003

Data Index: 535355 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1063526 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0449. Min Act: -0.0003

Data Index: 379844 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1650 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0456. Min Act: -0.0003

Data Index: 575849 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0465. Min Act: -0.0003

Data Index: 971837 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1110607 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0434. Min Act: -0.0004

Data Index: 72488 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0428. Min Act: -0.0003

Data Index: 535019 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0438. Min Act: -0.0003

Data Index: 605768 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0418. Min Act: -0.0004

Data Index: 604592 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0421. Min Act: -0.0003

Data Index: 556464 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0400. Min Act: -0.0003

Data Index: 185516 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0421. Min Act: -0.0003

Data Index: 430358 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0411. Min Act: -0.0003

Data Index: 104331 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0424. Min Act: -0.0003

Data Index: 739458 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1040658 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0417. Min Act: -0.0003

Data Index: 562728 (C4 (Web Text))

Max Activating Token Index: 270