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

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

Neuron 3036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.8600. Min Act: -0.0002

Data Index: 799155 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.7314. Min Act: -0.0002

Data Index: 1325328 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.6305. Min Act: -0.0002

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.5449. Min Act: -0.0002

Data Index: 970555 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.5337. Min Act: -0.0002

Data Index: 529242 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.5042. Min Act: -0.0002

Data Index: 698520 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4900. Min Act: -0.0002

Data Index: 154853 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4820. Min Act: -0.0002

Data Index: 841767 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4334. Min Act: -0.0002

Data Index: 523719 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4488. Min Act: -0.0002

Data Index: 1218558 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4642. Min Act: -0.0002

Data Index: 676705 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4229. Min Act: -0.0002

Data Index: 403915 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4367. Min Act: -0.0002

Data Index: 529840 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4362. Min Act: -0.0002

Data Index: 392523 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4331. Min Act: -0.0002

Data Index: 182807 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.3888. Min Act: -0.0002

Data Index: 359050 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4143. Min Act: -0.0002

Data Index: 1260171 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4381. Min Act: -0.0002

Data Index: 1271941 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4188. Min Act: -0.0002

Data Index: 429528 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.8600. Min Range: -0.8600

Max Act: 0.4139. Min Act: -0.0002

Data Index: 1167758 (C4 (Web Text))

Max Activating Token Index: 113