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

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

Neuron 2761 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0000

Data Index: 969139 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0587. Min Act: -0.0000

Data Index: 282405 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1034911 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1290908 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1270552 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1357450 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1006951 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0455. Min Act: -0.0000

Data Index: 952248 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1027417 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0399. Min Act: -0.0000

Data Index: 475412 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0407. Min Act: -0.0000

Data Index: 14784 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1245673 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0385. Min Act: -0.0000

Data Index: 742211 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0391. Min Act: -0.0000

Data Index: 560849 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0375. Min Act: -0.0000

Data Index: 219015 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0367. Min Act: -0.0000

Data Index: 287382 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1373701 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0379. Min Act: -0.0000

Data Index: 831325 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0373. Min Act: -0.0000

Data Index: 545476 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1274841 (C4 (Web Text))

Max Activating Token Index: 562