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

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

Neuron 618 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.5380. Min Act: -0.0001

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.6421. Min Act: -0.0001

Data Index: 897625 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.1615. Min Act: -0.0001

Data Index: 670333 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.1449. Min Act: -0.0001

Data Index: 1124399 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.2656. Min Act: -0.0001

Data Index: 117758 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8469. Min Act: -0.0001

Data Index: 431386 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.1933. Min Act: -0.0001

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.3110. Min Act: -0.0001

Data Index: 842861 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.0172. Min Act: -0.0001

Data Index: 823332 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.0432. Min Act: -0.0001

Data Index: 52595 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.9960. Min Act: -0.0001

Data Index: 860970 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8249. Min Act: -0.0001

Data Index: 47773 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 3.6421. Min Range: -3.6421

Max Act: 3.0816. Min Act: -0.0001

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.9351. Min Act: -0.0001

Data Index: 1072705 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8937. Min Act: -0.0001

Data Index: 297504 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.6467. Min Act: -0.0001

Data Index: 175330 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.9023. Min Act: -0.0001

Data Index: 662744 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.7683. Min Act: -0.0001

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.8648. Min Act: -0.0001

Data Index: 574837 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 3.6421. Min Range: -3.6421

Max Act: 2.7000. Min Act: -0.0001

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 49