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

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

Neuron 5178 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3735. Min Range: -7.3735

Max Act: 7.3735. Min Act: -0.0000

Data Index: 557682 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.6183. Min Act: -0.0000

Data Index: 1100633 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.3971. Min Act: -0.0000

Data Index: 952922 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.3477. Min Act: 0.0000

Data Index: 106664 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.3303. Min Act: 0.0000

Data Index: 1316094 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.3266. Min Act: -0.0000

Data Index: 693564 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.0976. Min Act: -0.0000

Data Index: 1037855 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.2265. Min Act: 0.0000

Data Index: 216608 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.3962. Min Act: 0.0000

Data Index: 1272389 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.1850. Min Act: -0.0000

Data Index: 108019 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.1467. Min Act: 0.0000

Data Index: 601604 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.1047. Min Act: 0.0000

Data Index: 752299 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.0770. Min Act: 0.0000

Data Index: 320965 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.0432. Min Act: 0.0000

Data Index: 999421 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.1262. Min Act: -0.0000

Data Index: 169507 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 7.3735. Min Range: -7.3735

Max Act: 5.5640. Min Act: -0.0000

Data Index: 179284 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 7.3735. Min Range: -7.3735

Max Act: 5.9602. Min Act: -0.0000

Data Index: 1110789 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 7.3735. Min Range: -7.3735

Max Act: 5.6616. Min Act: -0.0000

Data Index: 1132320 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 7.3735. Min Range: -7.3735

Max Act: 5.5823. Min Act: -0.0000

Data Index: 812538 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 7.3735. Min Range: -7.3735

Max Act: 5.5850. Min Act: -0.0000

Data Index: 542998 (C4 (Web Text))

Max Activating Token Index: 6