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

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

Neuron 1649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.6422. Min Act: -0.0000

Data Index: 119268 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5796. Min Act: -0.0000

Data Index: 761278 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1008358 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5652. Min Act: 0.0001

Data Index: 720080 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1201416 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5311. Min Act: -0.0001

Data Index: 717359 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5430. Min Act: -0.0000

Data Index: 839999 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5289. Min Act: -0.0000

Data Index: 517478 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4709. Min Act: -0.0000

Data Index: 92466 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4916. Min Act: -0.0000

Data Index: 843944 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5074. Min Act: -0.0000

Data Index: 349716 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4823. Min Act: -0.0000

Data Index: 163946 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1205937 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4866. Min Act: -0.0000

Data Index: 331113 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4654. Min Act: -0.0001

Data Index: 485323 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1100372 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1140843 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4394. Min Act: -0.0001

Data Index: 912714 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4653. Min Act: -0.0000

Data Index: 159531 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4507. Min Act: -0.0000

Data Index: 885752 (C4 (Web Text))

Max Activating Token Index: 219