Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 324 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4768. Min Act: -0.0000

Data Index: 488425 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4835. Min Act: -0.0000

Data Index: 540617 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4378. Min Act: -0.0001

Data Index: 878125 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4373. Min Act: -0.0001

Data Index: 399592 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4571. Min Act: -0.0001

Data Index: 1017192 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1303037 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1160147 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4194. Min Act: -0.0000

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4317. Min Act: -0.0001

Data Index: 187181 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3954. Min Act: -0.0000

Data Index: 955408 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3978. Min Act: 0.0000

Data Index: 385315 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3869. Min Act: -0.0001

Data Index: 1065392 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1298066 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3954. Min Act: -0.0000

Data Index: 748134 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1263003 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3504. Min Act: -0.0000

Data Index: 215509 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3579. Min Act: -0.0001

Data Index: 677996 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3705. Min Act: -0.0000

Data Index: 990518 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3795. Min Act: -0.0000

Data Index: 755697 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3675. Min Act: -0.0000

Data Index: 684681 (C4 (Web Text))

Max Activating Token Index: 568