Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6738. Min Act: -0.0001

Data Index: 339676 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6613. Min Act: -0.0001

Data Index: 464825 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5423. Min Act: -0.0001

Data Index: 914391 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4377. Min Act: -0.0001

Data Index: 310043 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1345005 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5313. Min Act: -0.0001

Data Index: 60975 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5288. Min Act: -0.0001

Data Index: 534099 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5193. Min Act: -0.0001

Data Index: 360141 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1069200 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1084519 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5230. Min Act: -0.0001

Data Index: 1274011 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4940. Min Act: -0.0001

Data Index: 766734 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1054116 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4852. Min Act: -0.0001

Data Index: 590990 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5174. Min Act: -0.0001

Data Index: 976442 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4803. Min Act: -0.0001

Data Index: 761320 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4844. Min Act: -0.0001

Data Index: 492109 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4763. Min Act: -0.0000

Data Index: 720347 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5099. Min Act: -0.0001

Data Index: 1122381 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5401. Min Act: -0.0001

Data Index: 809955 (C4 (Web Text))

Max Activating Token Index: 628