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

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

Neuron 4634 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.2835. Min Act: 0.0001

Data Index: 782227 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.2024. Min Act: -0.0000

Data Index: 873945 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0355. Min Act: 0.0001

Data Index: 890571 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.2835. Min Range: -1.2835

Max Act: 1.0143. Min Act: -0.0000

Data Index: 60964 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9242. Min Act: 0.0000

Data Index: 1207301 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9633. Min Act: 0.0000

Data Index: 922394 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9516. Min Act: 0.0001

Data Index: 548508 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.9218. Min Act: -0.0000

Data Index: 486011 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8270. Min Act: 0.0001

Data Index: 954715 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8527. Min Act: -0.0000

Data Index: 494912 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8373. Min Act: 0.0000

Data Index: 336512 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8395. Min Act: 0.0000

Data Index: 599284 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8330. Min Act: 0.0001

Data Index: 1299609 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8210. Min Act: 0.0001

Data Index: 945598 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8106. Min Act: 0.0000

Data Index: 952201 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.8076. Min Act: -0.0000

Data Index: 265740 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.7984. Min Act: 0.0001

Data Index: 97586 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.7925. Min Act: 0.0001

Data Index: 753637 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.7824. Min Act: -0.0000

Data Index: 464410 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.2835. Min Range: -1.2835

Max Act: 0.7777. Min Act: -0.0000

Data Index: 202723 (C4 (Web Text))

Max Activating Token Index: 712