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

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

Neuron 305 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.6096. Min Act: -0.0001

Data Index: 1085664 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5945. Min Act: -0.0001

Data Index: 526530 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.6136. Min Act: -0.0001

Data Index: 849434 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5665. Min Act: -0.0000

Data Index: 751794 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5816. Min Act: -0.0000

Data Index: 522436 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5453. Min Act: -0.0000

Data Index: 962313 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5417. Min Act: -0.0000

Data Index: 320038 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5412. Min Act: -0.0000

Data Index: 286018 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1114152 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1193931 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5495. Min Act: -0.0000

Data Index: 504927 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5196. Min Act: -0.0000

Data Index: 533399 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4764. Min Act: -0.0001

Data Index: 1150915 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5018. Min Act: -0.0000

Data Index: 878556 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5356. Min Act: -0.0000

Data Index: 916067 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5286. Min Act: -0.0000

Data Index: 29465 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4588. Min Act: -0.0000

Data Index: 300991 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5213. Min Act: -0.0001

Data Index: 86036 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1314284 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.6136. Min Range: -0.6136

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1265682 (C4 (Web Text))

Max Activating Token Index: 747