Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3267 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1218434 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1398. Min Act: -0.0000

Data Index: 316938 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1340299 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1750. Min Act: -0.0000

Data Index: 830219 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1114. Min Act: -0.0000

Data Index: 199954 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1029. Min Act: -0.0000

Data Index: 360836 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1343694 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0771. Min Act: -0.0000

Data Index: 736243 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0883. Min Act: -0.0000

Data Index: 822409 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1204975 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1204535 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0065. Min Act: -0.0000

Data Index: 199516 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0051. Min Act: -0.0000

Data Index: 714077 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0711. Min Act: -0.0000

Data Index: 835791 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9969. Min Act: -0.0001

Data Index: 180260 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1259396 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0566. Min Act: -0.0000

Data Index: 628772 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1071356 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0802. Min Act: -0.0000

Data Index: 916264 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0418. Min Act: -0.0000

Data Index: 487462 (C4 (Web Text))

Max Activating Token Index: 762