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

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

Neuron 1418 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.0702. Min Act: -0.0004

Data Index: 101127 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.2352. Min Act: -0.0004

Data Index: 1033880 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.8435. Min Act: -0.0004

Data Index: 69167 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1148. Min Act: -0.0004

Data Index: 429864 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1004. Min Act: -0.0004

Data Index: 678511 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1289. Min Act: -0.0004

Data Index: 372084 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.0197. Min Act: -0.0004

Data Index: 387528 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.0506. Min Act: -0.0004

Data Index: 329780 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1477. Min Act: -0.0004

Data Index: 485695 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1471. Min Act: -0.0004

Data Index: 862235 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1800. Min Act: -0.0004

Data Index: 294139 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.0374. Min Act: -0.0004

Data Index: 473350 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1755. Min Act: -0.0004

Data Index: 154854 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1700. Min Act: -0.0004

Data Index: 158466 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1654. Min Act: -0.0004

Data Index: 842899 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.3547. Min Act: -0.0004

Data Index: 570521 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.2001. Min Act: -0.0004

Data Index: 675649 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.1635. Min Act: -0.0004

Data Index: 682035 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.3547. Min Range: -1.3547

Max Act: 0.9295. Min Act: -0.0004

Data Index: 361152 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.3547. Min Range: -1.3547

Max Act: 1.0553. Min Act: -0.0004

Data Index: 1358379 (C4 (Web Text))

Max Activating Token Index: 312