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

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

Neuron 4601 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8507. Min Act: -0.0001

Data Index: 594286 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8688. Min Act: -0.0001

Data Index: 862164 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8953. Min Act: -0.0001

Data Index: 1358308 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1320426 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8377. Min Act: -0.0001

Data Index: 850714 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7715. Min Act: -0.0001

Data Index: 966261 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8061. Min Act: -0.0001

Data Index: 769270 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7687. Min Act: -0.0001

Data Index: 1334574 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8118. Min Act: -0.0001

Data Index: 795945 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7884. Min Act: -0.0001

Data Index: 977738 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7256. Min Act: -0.0001

Data Index: 426846 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7196. Min Act: -0.0001

Data Index: 909042 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7220. Min Act: -0.0001

Data Index: 1002758 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7270. Min Act: -0.0001

Data Index: 1302792 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6462. Min Act: -0.0001

Data Index: 569246 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7040. Min Act: -0.0001

Data Index: 577643 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7359. Min Act: -0.0001

Data Index: 1053730 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6283. Min Act: -0.0001

Data Index: 33156 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6360. Min Act: -0.0001

Data Index: 1300525 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6294. Min Act: -0.0001

Data Index: 1052745 (C4 (Web Text))

Max Activating Token Index: 923