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

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

Neuron 4124 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9348. Min Act: -0.0001

Data Index: 888620 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8185. Min Act: -0.0001

Data Index: 562090 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8285. Min Act: -0.0001

Data Index: 82621 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7283. Min Act: -0.0001

Data Index: 689445 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6815. Min Act: -0.0001

Data Index: 851470 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6850. Min Act: -0.0001

Data Index: 62403 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6710. Min Act: -0.0001

Data Index: 28835 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6801. Min Act: -0.0001

Data Index: 86022 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1278534 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6540. Min Act: -0.0001

Data Index: 900173 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6073. Min Act: -0.0001

Data Index: 466616 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5807. Min Act: -0.0001

Data Index: 825204 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1273141 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6344. Min Act: -0.0001

Data Index: 252584 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6196. Min Act: -0.0001

Data Index: 495837 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7089. Min Act: -0.0001

Data Index: 443571 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5926. Min Act: -0.0001

Data Index: 1162734 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6109. Min Act: -0.0001

Data Index: 1342350 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6378. Min Act: -0.0001

Data Index: 1097209 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1196471 (C4 (Web Text))

Max Activating Token Index: 365