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

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

Neuron 5970 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: 3.7509. Min Range: -3.7509

Max Act: 3.7509. Min Act: -0.0000

Data Index: 1164616 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.7295. Min Act: -0.0000

Data Index: 1054871 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.3431. Min Act: -0.0000

Data Index: 408491 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.4252. Min Act: -0.0000

Data Index: 103076 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.5779. Min Act: -0.0000

Data Index: 823310 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.1388. Min Act: -0.0000

Data Index: 1069150 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.9583. Min Act: -0.0000

Data Index: 35296 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.0940. Min Act: -0.0000

Data Index: 1309094 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.0146. Min Act: -0.0000

Data Index: 596367 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.0653. Min Act: -0.0000

Data Index: 986698 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.9277. Min Act: -0.0000

Data Index: 274741 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.8823. Min Act: -0.0000

Data Index: 632610 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.6871. Min Act: -0.0000

Data Index: 580562 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.6414. Min Act: -0.0000

Data Index: 832783 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.7509. Min Range: -3.7509

Max Act: 3.0027. Min Act: -0.0000

Data Index: 109579 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.5512. Min Act: -0.0000

Data Index: 605202 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.8244. Min Act: -0.0000

Data Index: 1184673 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.5361. Min Act: -0.0000

Data Index: 708386 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.6360. Min Act: -0.0000

Data Index: 1225566 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 3.7509. Min Range: -3.7509

Max Act: 2.6511. Min Act: -0.0000

Data Index: 315883 (C4 (Web Text))

Max Activating Token Index: 487