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

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

Neuron 1779 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1546382 (Python Code)

Max Activating Token Index: 685

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1635712 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1055443 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1151627 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0485. Min Act: -0.0000

Data Index: 160486 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0460. Min Act: -0.0001

Data Index: 16609 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0405. Min Act: -0.0000

Data Index: 851292 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0410. Min Act: -0.0000

Data Index: 954778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1005756 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1103715 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0359. Min Act: -0.0000

Data Index: 795094 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0352. Min Act: -0.0000

Data Index: 1411015 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0345. Min Act: -0.0000

Data Index: 102332 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0382. Min Act: -0.0000

Data Index: 604776 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0369. Min Act: -0.0000

Data Index: 254660 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0381. Min Act: -0.0000

Data Index: 569116 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1135418 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0339. Min Act: -0.0000

Data Index: 891508 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0325. Min Act: -0.0000

Data Index: 499441 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1359163 (C4 (Web Text))

Max Activating Token Index: 217