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

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

Neuron 283 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1264059 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3217. Min Act: -0.0001

Data Index: 916990 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3517. Min Act: -0.0001

Data Index: 549516 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1103272 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3721. Min Act: -0.0001

Data Index: 629727 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3490. Min Act: -0.0001

Data Index: 1211819 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3178. Min Act: -0.0002

Data Index: 771653 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3379. Min Act: -0.0001

Data Index: 9626 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3348. Min Act: -0.0001

Data Index: 169977 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1109786 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1252596 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1188188 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1235859 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3034. Min Act: -0.0001

Data Index: 773927 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3073. Min Act: -0.0001

Data Index: 555428 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3166. Min Act: -0.0001

Data Index: 246028 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3263. Min Act: -0.0001

Data Index: 798123 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3403. Min Act: -0.0001

Data Index: 666035 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2908. Min Act: -0.0001

Data Index: 706020 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3054. Min Act: -0.0001

Data Index: 423494 (C4 (Web Text))

Max Activating Token Index: 572