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

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

Neuron 4113 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: 0.7142. Min Range: -0.7142

Max Act: 0.7142. Min Act: -0.0000

Data Index: 472608 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1133170 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6268. Min Act: -0.0000

Data Index: 243793 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5497. Min Act: -0.0000

Data Index: 853032 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1104084 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5931. Min Act: -0.0000

Data Index: 237257 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5639. Min Act: -0.0000

Data Index: 378598 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5436. Min Act: -0.0000

Data Index: 63437 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5276. Min Act: -0.0000

Data Index: 502018 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5458. Min Act: -0.0000

Data Index: 381413 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1292557 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5008. Min Act: -0.0000

Data Index: 118983 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1255691 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4860. Min Act: -0.0000

Data Index: 460646 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5008. Min Act: -0.0000

Data Index: 192689 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1351475 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4761. Min Act: -0.0000

Data Index: 69891 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4633. Min Act: -0.0000

Data Index: 189567 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4736. Min Act: -0.0000

Data Index: 518880 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.4715. Min Act: -0.0000

Data Index: 804902 (C4 (Web Text))

Max Activating Token Index: 653