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

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

Neuron 1642 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: 2.0480. Min Range: -2.0480

Max Act: 2.0152. Min Act: -0.0000

Data Index: 951973 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.9750. Min Act: -0.0000

Data Index: 695190 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 2.0480. Min Range: -2.0480

Max Act: 2.0480. Min Act: -0.0000

Data Index: 1288120 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.9671. Min Act: -0.0000

Data Index: 1198143 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 2.0480. Min Range: -2.0480

Max Act: 2.0183. Min Act: -0.0000

Data Index: 404247 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.8569. Min Act: -0.0000

Data Index: 913613 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.7514. Min Act: -0.0000

Data Index: 790674 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1326688 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.7800. Min Act: -0.0000

Data Index: 122041 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1174812 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.5389. Min Act: -0.0000

Data Index: 713243 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.7066. Min Act: -0.0000

Data Index: 670211 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.6181. Min Act: -0.0000

Data Index: 962124 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.7305. Min Act: -0.0000

Data Index: 169386 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1270291 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1022466 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.5505. Min Act: -0.0000

Data Index: 845610 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.6297. Min Act: -0.0000

Data Index: 624521 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1342927 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 2.0480. Min Range: -2.0480

Max Act: 1.4108. Min Act: -0.0000

Data Index: 952304 (C4 (Web Text))

Max Activating Token Index: 463