Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3218 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1176309 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0543. Min Act: -0.0003

Data Index: 743625 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0500. Min Act: -0.0003

Data Index: 569535 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0519. Min Act: -0.0003

Data Index: 802960 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0003

Data Index: 773129 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0477. Min Act: -0.0003

Data Index: 65994 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0516. Min Act: -0.0003

Data Index: 863959 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0480. Min Act: -0.0003

Data Index: 760284 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0508. Min Act: -0.0003

Data Index: 984874 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0484. Min Act: -0.0003

Data Index: 414933 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0481. Min Act: -0.0004

Data Index: 359239 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0487. Min Act: -0.0003

Data Index: 47849 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0452. Min Act: -0.0003

Data Index: 253379 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0470. Min Act: -0.0003

Data Index: 352692 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0450. Min Act: -0.0003

Data Index: 852497 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0450. Min Act: -0.0003

Data Index: 668808 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1109838 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0450. Min Act: -0.0003

Data Index: 64964 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0446. Min Act: -0.0004

Data Index: 300934 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0466. Min Act: -0.0003

Data Index: 331390 (C4 (Web Text))

Max Activating Token Index: 225