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

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

Neuron 2469 in Layer 1

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: 1.1321. Min Range: -1.1321

Max Act: 1.1321. Min Act: -0.0003

Data Index: 99263 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.1015. Min Act: -0.0002

Data Index: 361139 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.1061. Min Act: -0.0002

Data Index: 252200 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.0552. Min Act: -0.0002

Data Index: 490792 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.0243. Min Act: -0.0002

Data Index: 1350795 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.0342. Min Act: -0.0002

Data Index: 32045 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.0167. Min Act: -0.0002

Data Index: 327233 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9971. Min Act: -0.0002

Data Index: 648733 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.1321. Min Range: -1.1321

Max Act: 1.0042. Min Act: -0.0002

Data Index: 1362360 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9882. Min Act: -0.0002

Data Index: 897683 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9830. Min Act: -0.0002

Data Index: 538884 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9442. Min Act: -0.0002

Data Index: 432092 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9437. Min Act: -0.0002

Data Index: 479562 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9580. Min Act: -0.0002

Data Index: 418967 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9721. Min Act: -0.0002

Data Index: 468341 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9635. Min Act: -0.0002

Data Index: 1519484 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9483. Min Act: -0.0002

Data Index: 1064911 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9697. Min Act: -0.0002

Data Index: 445142 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9587. Min Act: -0.0002

Data Index: 352699 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.1321. Min Range: -1.1321

Max Act: 0.9350. Min Act: -0.0002

Data Index: 265745 (C4 (Web Text))

Max Activating Token Index: 531