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

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

Neuron 5967 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: 0.3893. Min Range: -0.3893

Max Act: 0.3893. Min Act: -0.0000

Data Index: 178114 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.3335. Min Act: -0.0000

Data Index: 670897 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2806. Min Act: -0.0000

Data Index: 251916 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1279138 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.3263. Min Act: -0.0000

Data Index: 70117 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2767. Min Act: -0.0000

Data Index: 546092 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2900. Min Act: -0.0000

Data Index: 98044 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1050183 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2665. Min Act: -0.0000

Data Index: 480505 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2808. Min Act: -0.0000

Data Index: 596165 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1348810 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1341714 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2519. Min Act: -0.0000

Data Index: 19873 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2588. Min Act: -0.0000

Data Index: 296063 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2563. Min Act: -0.0000

Data Index: 473973 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2331. Min Act: -0.0000

Data Index: 997482 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2525. Min Act: -0.0000

Data Index: 659190 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2604. Min Act: -0.0000

Data Index: 73288 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2471. Min Act: -0.0000

Data Index: 920826 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.3893. Min Range: -0.3893

Max Act: 0.2328. Min Act: -0.0000

Data Index: 356266 (C4 (Web Text))

Max Activating Token Index: 673