Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4187 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.4584. Min Act: -0.0000

Data Index: 109824 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3322. Min Act: -0.0000

Data Index: 692506 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1253891 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2996. Min Act: -0.0000

Data Index: 664476 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3001. Min Act: -0.0000

Data Index: 404938 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2898. Min Act: -0.0000

Data Index: 791654 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2909. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1243830 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2821. Min Act: -0.0000

Data Index: 155209 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1034128 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2561. Min Act: -0.0000

Data Index: 518482 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2768. Min Act: -0.0000

Data Index: 943992 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1095943 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2714. Min Act: -0.0000

Data Index: 170209 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1280344 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2719. Min Act: -0.0000

Data Index: 4526 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2519. Min Act: -0.0000

Data Index: 298179 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2730. Min Act: -0.0000

Data Index: 76211 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1020171 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.4584. Min Range: -0.4584

Max Act: 0.2729. Min Act: -0.0000

Data Index: 358236 (C4 (Web Text))

Max Activating Token Index: 192