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

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

Neuron 4947 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.5011. Min Act: -0.0000

Data Index: 472770 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.5407. Min Act: -0.0000

Data Index: 417037 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.5091. Min Act: -0.0000

Data Index: 1129089 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.3020. Min Act: -0.0000

Data Index: 767572 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.0348. Min Act: -0.0000

Data Index: 975651 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1530. Min Act: -0.0000

Data Index: 704032 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.1016. Min Act: -0.0000

Data Index: 1263826 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.9879. Min Act: -0.0000

Data Index: 542351 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.9908. Min Act: -0.0000

Data Index: 1289612 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.9872. Min Act: -0.0000

Data Index: 45917 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.8626. Min Act: -0.0000

Data Index: 208303 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.5407. Min Range: -2.5407

Max Act: 2.0658. Min Act: -0.0000

Data Index: 306714 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.9616. Min Act: -0.0000

Data Index: 1303715 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.8507. Min Act: -0.0000

Data Index: 372539 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.9012. Min Act: -0.0000

Data Index: 760717 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.8827. Min Act: -0.0000

Data Index: 254285 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1193654 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1332729 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.7410. Min Act: -0.0000

Data Index: 119072 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 2.5407. Min Range: -2.5407

Max Act: 1.7142. Min Act: -0.0000

Data Index: 1057205 (C4 (Web Text))

Max Activating Token Index: 337