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

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

Neuron 2168 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2337. Min Act: -0.0001

Data Index: 208978 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2155. Min Act: -0.0001

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1897. Min Act: -0.0001

Data Index: 145560 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1856. Min Act: -0.0001

Data Index: 309118 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1016023 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1799. Min Act: -0.0001

Data Index: 440134 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1332522 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1743. Min Act: -0.0001

Data Index: 374992 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1745. Min Act: -0.0001

Data Index: 683767 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1720. Min Act: -0.0001

Data Index: 651464 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1702. Min Act: -0.0001

Data Index: 528654 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1654. Min Act: -0.0001

Data Index: 512095 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1090291 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1226616 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1268338 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1615. Min Act: -0.0001

Data Index: 796813 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1272687 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1147353 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1032802 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1329693 (C4 (Web Text))

Max Activating Token Index: 790