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

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

Neuron 4318 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1732. Min Range: -2.1732

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1182257 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1331438 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.2153. Min Act: -0.0000

Data Index: 964870 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.0844. Min Act: -0.0000

Data Index: 871643 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.0321. Min Act: -0.0000

Data Index: 128190 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1277769 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.0418. Min Act: -0.0000

Data Index: 607350 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.0242. Min Act: -0.0000

Data Index: 830034 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.9644. Min Act: -0.0000

Data Index: 270543 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.9254. Min Act: -0.0000

Data Index: 184461 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.9185. Min Act: -0.0000

Data Index: 41288 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.1732. Min Range: -2.1732

Max Act: 1.0018. Min Act: -0.0000

Data Index: 364335 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1259223 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.9433. Min Act: -0.0000

Data Index: 637683 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.7723. Min Act: -0.0000

Data Index: 616326 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.8955. Min Act: -0.0000

Data Index: 488986 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.8442. Min Act: -0.0000

Data Index: 458977 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.8345. Min Act: -0.0000

Data Index: 200477 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.9068. Min Act: -0.0000

Data Index: 460980 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 2.1732. Min Range: -2.1732

Max Act: 0.7929. Min Act: -0.0000

Data Index: 708046 (C4 (Web Text))

Max Activating Token Index: 627