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

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

Neuron 5310 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0292. Min Range: -2.0292

Max Act: 2.0268. Min Act: -0.0000

Data Index: 4188 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.0292. Min Range: -2.0292

Max Act: 2.0292. Min Act: -0.0000

Data Index: 1205623 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 2.0292. Min Range: -2.0292

Max Act: 2.0069. Min Act: -0.0000

Data Index: 173940 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.7081. Min Act: -0.0000

Data Index: 649302 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.6972. Min Act: -0.0000

Data Index: 346927 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.6763. Min Act: -0.0000

Data Index: 92784 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.5351. Min Act: -0.0000

Data Index: 826293 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.5212. Min Act: -0.0000

Data Index: 704018 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4852. Min Act: -0.0000

Data Index: 619651 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4902. Min Act: -0.0000

Data Index: 886058 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4600. Min Act: -0.0000

Data Index: 59499 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4609. Min Act: -0.0000

Data Index: 728418 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4407. Min Act: -0.0000

Data Index: 319338 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4415. Min Act: -0.0000

Data Index: 383797 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.4164. Min Act: -0.0000

Data Index: 347246 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.3108. Min Act: -0.0000

Data Index: 73305 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.3826. Min Act: -0.0000

Data Index: 166576 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.3830. Min Act: -0.0000

Data Index: 300638 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1225975 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 2.0292. Min Range: -2.0292

Max Act: 1.3559. Min Act: -0.0000

Data Index: 753696 (C4 (Web Text))

Max Activating Token Index: 775