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

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

Neuron 400 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: 0.5141. Min Range: -0.5141

Max Act: 0.5141. Min Act: -0.0000

Data Index: 192983 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.5132. Min Act: -0.0000

Data Index: 379179 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4906. Min Act: -0.0000

Data Index: 870937 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.5054. Min Act: -0.0000

Data Index: 176687 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1221172 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4809. Min Act: -0.0000

Data Index: 326589 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4793. Min Act: -0.0000

Data Index: 680870 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4975. Min Act: -0.0000

Data Index: 126383 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4882. Min Act: -0.0000

Data Index: 547118 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4717. Min Act: -0.0000

Data Index: 222802 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4939. Min Act: -0.0000

Data Index: 744568 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1188417 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4607. Min Act: -0.0000

Data Index: 601574 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1224082 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4815. Min Act: -0.0000

Data Index: 532914 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4656. Min Act: -0.0000

Data Index: 427891 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4617. Min Act: -0.0000

Data Index: 724935 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1050876 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4302. Min Act: -0.0000

Data Index: 793293 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.5141. Min Range: -0.5141

Max Act: 0.4465. Min Act: -0.0000

Data Index: 701850 (C4 (Web Text))

Max Activating Token Index: 507