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

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

Neuron 4536 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: 4.4584. Min Range: -4.4584

Max Act: 4.4584. Min Act: -0.0000

Data Index: 689826 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 4.4584. Min Range: -4.4584

Max Act: 4.0090. Min Act: -0.0000

Data Index: 112514 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 4.4584. Min Range: -4.4584

Max Act: 4.2606. Min Act: -0.0000

Data Index: 878301 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 4.4584. Min Range: -4.4584

Max Act: 4.0122. Min Act: -0.0000

Data Index: 501174 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.7543. Min Act: -0.0000

Data Index: 391391 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.8785. Min Act: -0.0000

Data Index: 546840 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.8374. Min Act: -0.0000

Data Index: 165389 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.8246. Min Act: -0.0000

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.7940. Min Act: -0.0000

Data Index: 485797 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.7682. Min Act: -0.0000

Data Index: 111046 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.7061. Min Act: -0.0000

Data Index: 283575 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.8347. Min Act: -0.0000

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.7887. Min Act: -0.0000

Data Index: 1009159 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.4523. Min Act: -0.0000

Data Index: 1165395 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.5825. Min Act: -0.0000

Data Index: 382541 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.6972. Min Act: -0.0000

Data Index: 1013431 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.5242. Min Act: -0.0000

Data Index: 56330 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.5001. Min Act: -0.0000

Data Index: 206370 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.4775. Min Act: -0.0000

Data Index: 209858 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 4.4584. Min Range: -4.4584

Max Act: 3.4575. Min Act: -0.0000

Data Index: 1208598 (C4 (Web Text))

Max Activating Token Index: 252