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

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

Neuron 520 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: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0003

Data Index: 223262 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1153220 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0598. Min Act: -0.0003

Data Index: 106732 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0585. Min Act: -0.0003

Data Index: 874088 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0571. Min Act: -0.0003

Data Index: 62420 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1321424 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1010186 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0547. Min Act: -0.0003

Data Index: 206609 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0523. Min Act: -0.0003

Data Index: 117608 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0532. Min Act: -0.0003

Data Index: 873219 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0493. Min Act: -0.0003

Data Index: 10612 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0515. Min Act: -0.0003

Data Index: 488898 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0542. Min Act: -0.0003

Data Index: 156860 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0506. Min Act: -0.0003

Data Index: 620975 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1256416 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0433. Min Act: -0.0003

Data Index: 880302 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0480. Min Act: -0.0003

Data Index: 942344 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0517. Min Act: -0.0003

Data Index: 742306 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1159486 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0493. Min Act: -0.0003

Data Index: 924912 (C4 (Web Text))

Max Activating Token Index: 432