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

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

Neuron 3051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.8719. Min Act: -0.0000

Data Index: 668450 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.8556. Min Act: -0.0000

Data Index: 800188 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7934. Min Act: -0.0000

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.8196. Min Act: -0.0000

Data Index: 600412 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1167559 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7865. Min Act: -0.0000

Data Index: 214541 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7445. Min Act: -0.0001

Data Index: 843458 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7301. Min Act: -0.0000

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1123985 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1291107 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7279. Min Act: -0.0000

Data Index: 565567 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1301764 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7887. Min Act: -0.0000

Data Index: 947581 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7210. Min Act: -0.0000

Data Index: 484421 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1305038 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6970. Min Act: -0.0000

Data Index: 682078 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7310. Min Act: -0.0000

Data Index: 424173 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7287. Min Act: -0.0000

Data Index: 780909 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1278123 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7286. Min Act: -0.0000

Data Index: 529916 (C4 (Web Text))

Max Activating Token Index: 69