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

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

Neuron 4369 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1543418 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1404713 (Python Code)

Max Activating Token Index: 559

Text #2

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1379481 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1585210 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1249997 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5303. Min Act: -0.0000

Data Index: 606130 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1397669 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4440. Min Act: -0.0000

Data Index: 325703 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4749. Min Act: -0.0000

Data Index: 357955 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4305. Min Act: -0.0000

Data Index: 420320 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4832. Min Act: -0.0000

Data Index: 678381 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4981. Min Act: -0.0000

Data Index: 385960 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1246972 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4109. Min Act: -0.0000

Data Index: 663840 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4537. Min Act: -0.0000

Data Index: 118995 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4391. Min Act: -0.0000

Data Index: 20357 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4388. Min Act: -0.0000

Data Index: 389280 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4281. Min Act: -0.0000

Data Index: 567646 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1097123 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.4185. Min Act: -0.0000

Data Index: 234072 (C4 (Web Text))

Max Activating Token Index: 757