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

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

Neuron 4630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0417. Min Act: -0.0000

Data Index: 346365 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9397. Min Act: -0.0000

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0321. Min Act: -0.0000

Data Index: 980979 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0740. Min Act: -0.0000

Data Index: 289307 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9236. Min Act: -0.0000

Data Index: 415484 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8803. Min Act: -0.0000

Data Index: 550771 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0216. Min Act: -0.0000

Data Index: 68469 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9976. Min Act: -0.0000

Data Index: 699596 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9778. Min Act: -0.0000

Data Index: 55027 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1318366 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9920. Min Act: -0.0000

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9814. Min Act: -0.0000

Data Index: 444686 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0156. Min Act: -0.0000

Data Index: 521263 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9169. Min Act: -0.0000

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8953. Min Act: -0.0000

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0623. Min Act: -0.0000

Data Index: 1118047 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9418. Min Act: -0.0000

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8761. Min Act: -0.0000

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1071520 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8289. Min Act: -0.0000

Data Index: 282314 (C4 (Web Text))

Max Activating Token Index: 159