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

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

Neuron 2388 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: 0.9618. Min Range: -0.9618

Max Act: 0.9496. Min Act: -0.0000

Data Index: 975838 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.9618. Min Act: -0.0001

Data Index: 592873 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8807. Min Act: -0.0000

Data Index: 494302 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8952. Min Act: -0.0000

Data Index: 908308 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1332726 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8573. Min Act: -0.0001

Data Index: 554952 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1072314 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7819. Min Act: -0.0000

Data Index: 725846 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8679. Min Act: -0.0000

Data Index: 54900 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8234. Min Act: -0.0000

Data Index: 168180 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1230928 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1065830 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8109. Min Act: -0.0000

Data Index: 548245 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1110926 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7980. Min Act: -0.0001

Data Index: 355907 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7550. Min Act: -0.0000

Data Index: 125647 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1321124 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7712. Min Act: -0.0000

Data Index: 685010 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7717. Min Act: -0.0000

Data Index: 377306 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7217. Min Act: -0.0000

Data Index: 149355 (C4 (Web Text))

Max Activating Token Index: 183