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

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

Neuron 5454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1257593 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.6062. Min Act: -0.0000

Data Index: 175536 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5814. Min Act: -0.0000

Data Index: 891932 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1258837 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4947. Min Act: -0.0000

Data Index: 944172 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5330. Min Act: -0.0000

Data Index: 991258 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5410. Min Act: -0.0000

Data Index: 633450 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1258165 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5387. Min Act: -0.0000

Data Index: 85249 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1334352 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5142. Min Act: -0.0000

Data Index: 723973 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5164. Min Act: -0.0000

Data Index: 504143 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5131. Min Act: -0.0000

Data Index: 22526 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1348110 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4710. Min Act: -0.0000

Data Index: 516312 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4874. Min Act: -0.0000

Data Index: 173839 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5049. Min Act: -0.0000

Data Index: 863791 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4867. Min Act: -0.0000

Data Index: 681264 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1261536 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5003. Min Act: -0.0000

Data Index: 240065 (C4 (Web Text))

Max Activating Token Index: 129