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

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

Neuron 1469 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7797. Min Act: -0.0000

Data Index: 948662 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7353. Min Act: -0.0000

Data Index: 792249 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7886. Min Act: -0.0000

Data Index: 538339 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1575102 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6876. Min Act: -0.0000

Data Index: 132104 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1209985 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7031. Min Act: -0.0000

Data Index: 649920 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1379431 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6672. Min Act: -0.0000

Data Index: 519263 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7081. Min Act: -0.0000

Data Index: 744705 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1451461 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1634359 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1396056 (Python Code)

Max Activating Token Index: 815

Text #13

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6165. Min Act: -0.0000

Data Index: 840765 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6293. Min Act: -0.0000

Data Index: 40182 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1538892 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1510127 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1160646 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1525464 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1038683 (C4 (Web Text))

Max Activating Token Index: 513