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

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

Neuron 4455 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4344. Min Range: -2.4344

Max Act: 2.2218. Min Act: -0.0000

Data Index: 798439 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.4344. Min Range: -2.4344

Max Act: 2.4344. Min Act: -0.0000

Data Index: 200495 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.7333. Min Act: -0.0000

Data Index: 837705 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.7147. Min Act: -0.0000

Data Index: 1344726 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.5644. Min Act: -0.0000

Data Index: 896740 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.5896. Min Act: -0.0000

Data Index: 989013 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1314505 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.4053. Min Act: -0.0000

Data Index: 356591 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.3984. Min Act: -0.0000

Data Index: 234141 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.2985. Min Act: -0.0000

Data Index: 715238 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1062643 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1528548 (Python Code)

Max Activating Token Index: 470

Text #12

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1084496 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1075474 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.0789. Min Act: -0.0000

Data Index: 762895 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1409201 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.0696. Min Act: -0.0000

Data Index: 145590 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1293. Min Act: -0.0000

Data Index: 85403 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1279. Min Act: -0.0000

Data Index: 684412 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 2.4344. Min Range: -2.4344

Max Act: 1.1120. Min Act: -0.0000

Data Index: 630309 (C4 (Web Text))

Max Activating Token Index: 977