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

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

Neuron 4016 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.8720. Min Act: -0.0000

Data Index: 483013 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.8865. Min Act: -0.0000

Data Index: 992435 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7750. Min Act: -0.0000

Data Index: 317616 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1357368 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7625. Min Act: -0.0000

Data Index: 129595 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1194650 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1359692 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1072744 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6129. Min Act: -0.0000

Data Index: 348340 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6097. Min Act: -0.0000

Data Index: 211176 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6332. Min Act: -0.0000

Data Index: 291111 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6282. Min Act: -0.0000

Data Index: 612567 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6094. Min Act: -0.0000

Data Index: 660084 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6271. Min Act: -0.0000

Data Index: 77974 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6256. Min Act: -0.0000

Data Index: 929560 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1116988 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.5815. Min Act: -0.0000

Data Index: 535111 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1121501 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.5947. Min Act: -0.0000

Data Index: 531827 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.8865. Min Range: -0.8865

Max Act: 0.6081. Min Act: -0.0000

Data Index: 586039 (C4 (Web Text))

Max Activating Token Index: 893