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

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

Neuron 3239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.6445. Min Act: -0.0000

Data Index: 739297 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.6408. Min Act: -0.0000

Data Index: 267183 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5445. Min Act: -0.0000

Data Index: 145426 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5757. Min Act: -0.0000

Data Index: 787692 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5188. Min Act: -0.0000

Data Index: 589146 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5122. Min Act: -0.0001

Data Index: 206938 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5119. Min Act: 0.0000

Data Index: 541296 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.5245. Min Act: -0.0000

Data Index: 839006 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4978. Min Act: -0.0000

Data Index: 929142 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4954. Min Act: 0.0001

Data Index: 1198452 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4756. Min Act: -0.0000

Data Index: 979923 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4745. Min Act: -0.0000

Data Index: 517918 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4582. Min Act: -0.0001

Data Index: 651165 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1345784 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4781. Min Act: -0.0000

Data Index: 68226 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4583. Min Act: -0.0000

Data Index: 484621 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4869. Min Act: -0.0000

Data Index: 152768 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4452. Min Act: -0.0000

Data Index: 113461 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1271189 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.6445. Min Range: -0.6445

Max Act: 0.4648. Min Act: -0.0000

Data Index: 6064 (C4 (Web Text))

Max Activating Token Index: 527