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

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

Neuron 2774 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0001

Data Index: 642543 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1351299 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1210. Min Act: -0.0001

Data Index: 453703 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1091. Min Act: -0.0001

Data Index: 928337 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1274. Min Act: -0.0001

Data Index: 558770 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1245575 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1148428 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1288247 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1025047 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1281094 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0818. Min Act: -0.0001

Data Index: 732579 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0773. Min Act: -0.0001

Data Index: 268427 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0724. Min Act: -0.0001

Data Index: 779240 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0750. Min Act: -0.0001

Data Index: 238207 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0720. Min Act: -0.0001

Data Index: 822863 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1341846 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1229975 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1236449 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0710. Min Act: -0.0001

Data Index: 653263 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0706. Min Act: -0.0001

Data Index: 262022 (C4 (Web Text))

Max Activating Token Index: 968