Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1108 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8798. Min Act: -0.0001

Data Index: 992291 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1237438 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9295. Min Act: -0.0001

Data Index: 739077 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8671. Min Act: -0.0001

Data Index: 239039 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8432. Min Act: -0.0001

Data Index: 845338 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8653. Min Act: -0.0001

Data Index: 97162 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8238. Min Act: -0.0001

Data Index: 1014627 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8703. Min Act: -0.0001

Data Index: 885130 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7918. Min Act: -0.0001

Data Index: 214838 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8408. Min Act: -0.0001

Data Index: 101940 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8111. Min Act: -0.0001

Data Index: 1233624 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8324. Min Act: -0.0001

Data Index: 261566 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7992. Min Act: -0.0001

Data Index: 858980 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8205. Min Act: -0.0001

Data Index: 1006268 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7826. Min Act: -0.0001

Data Index: 206564 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1160670 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7593. Min Act: -0.0001

Data Index: 213812 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7813. Min Act: -0.0001

Data Index: 634598 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7758. Min Act: -0.0001

Data Index: 454863 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7769. Min Act: -0.0001

Data Index: 832332 (C4 (Web Text))

Max Activating Token Index: 459