Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4372 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1096044 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0607. Min Act: -0.0001

Data Index: 277209 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1133375 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0512. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0509. Min Act: -0.0001

Data Index: 45153 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0553. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0458. Min Act: -0.0001

Data Index: 973346 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0480. Min Act: -0.0001

Data Index: 414453 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0472. Min Act: -0.0001

Data Index: 80161 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0482. Min Act: -0.0001

Data Index: 468865 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1118137 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1508796 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0410. Min Act: -0.0001

Data Index: 868894 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0398. Min Act: -0.0001

Data Index: 939871 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1623848 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1023278 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1146001 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1289671 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1329883 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0348. Min Act: -0.0001

Data Index: 468126 (C4 (Web Text))

Max Activating Token Index: 730