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

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

Neuron 1386 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: 7.8773. Min Range: -7.8773

Max Act: 7.8773. Min Act: -0.0000

Data Index: 986214 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 7.8773. Min Range: -7.8773

Max Act: 7.1234. Min Act: -0.0000

Data Index: 1047094 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 7.8773. Min Range: -7.8773

Max Act: 7.1106. Min Act: -0.0000

Data Index: 325854 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 7.8773. Min Range: -7.8773

Max Act: 7.2635. Min Act: -0.0000

Data Index: 1062205 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.4313. Min Act: -0.0000

Data Index: 661554 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.6088. Min Act: -0.0000

Data Index: 1055576 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.3361. Min Act: -0.0000

Data Index: 753613 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.3286. Min Act: -0.0000

Data Index: 520423 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.7776. Min Act: -0.0000

Data Index: 1082125 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.0492. Min Act: -0.0000

Data Index: 541593 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.7782. Min Act: -0.0000

Data Index: 626727 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.9843. Min Act: -0.0000

Data Index: 458484 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.9715. Min Act: -0.0000

Data Index: 510660 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 7.8773. Min Range: -7.8773

Max Act: 6.1830. Min Act: -0.0000

Data Index: 1105157 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.7700. Min Act: -0.0000

Data Index: 225520 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.9511. Min Act: -0.0000

Data Index: 744234 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.9534. Min Act: -0.0000

Data Index: 84194 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.6435. Min Act: -0.0000

Data Index: 1256648 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.5820. Min Act: -0.0000

Data Index: 837756 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 7.8773. Min Range: -7.8773

Max Act: 5.9535. Min Act: -0.0000

Data Index: 890968 (C4 (Web Text))

Max Activating Token Index: 487