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

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

Neuron 1660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.8431. Min Act: -0.0001

Data Index: 1130436 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6862. Min Act: -0.0001

Data Index: 113479 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6450. Min Act: -0.0001

Data Index: 353284 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1282437 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1057544 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1254809 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6132. Min Act: -0.0001

Data Index: 1032749 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5691. Min Act: -0.0001

Data Index: 1062417 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5693. Min Act: -0.0001

Data Index: 740176 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5681. Min Act: -0.0001

Data Index: 53805 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5063. Min Act: -0.0001

Data Index: 272520 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5077. Min Act: -0.0001

Data Index: 1316235 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5100. Min Act: -0.0001

Data Index: 1003026 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4187. Min Act: -0.0001

Data Index: 836332 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4643. Min Act: -0.0001

Data Index: 997939 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4362. Min Act: -0.0001

Data Index: 528360 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4709. Min Act: -0.0001

Data Index: 808417 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4642. Min Act: -0.0001

Data Index: 858688 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4727. Min Act: -0.0001

Data Index: 1638949 (Python Code)

Max Activating Token Index: 234

Text #19

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.4977. Min Act: -0.0001

Data Index: 238282 (C4 (Web Text))

Max Activating Token Index: 208