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

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

Neuron 4565 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6759. Min Act: -0.0000

Data Index: 850244 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5638. Min Act: -0.0000

Data Index: 313157 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5656. Min Act: -0.0000

Data Index: 300260 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5623. Min Act: -0.0000

Data Index: 412040 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5981. Min Act: -0.0000

Data Index: 712475 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1296375 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5617. Min Act: -0.0000

Data Index: 251225 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5374. Min Act: -0.0000

Data Index: 813591 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1185938 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5692. Min Act: -0.0000

Data Index: 487134 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5182. Min Act: -0.0000

Data Index: 491335 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5246. Min Act: -0.0000

Data Index: 722366 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5935. Min Act: -0.0000

Data Index: 325853 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5020. Min Act: -0.0000

Data Index: 694946 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5105. Min Act: -0.0000

Data Index: 975147 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5235. Min Act: -0.0000

Data Index: 790088 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5236. Min Act: -0.0000

Data Index: 315418 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5587. Min Act: -0.0000

Data Index: 79188 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5001. Min Act: -0.0000

Data Index: 61300 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4901. Min Act: -0.0000

Data Index: 198535 (C4 (Web Text))

Max Activating Token Index: 467