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

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

Neuron 3223 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1095406 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1766. Min Act: -0.0000

Data Index: 509861 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1546. Min Act: -0.0000

Data Index: 992900 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1074618 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1166076 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1815. Min Act: -0.0000

Data Index: 19278 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.0279. Min Act: -0.0000

Data Index: 406104 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1348103 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1574. Min Act: -0.0000

Data Index: 690471 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1262745 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1502. Min Act: -0.0000

Data Index: 731490 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1308507 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1172. Min Act: -0.0000

Data Index: 698667 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1143. Min Act: -0.0000

Data Index: 487464 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.1051. Min Act: -0.0000

Data Index: 533806 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.0985. Min Act: -0.0000

Data Index: 890794 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.0118. Min Act: -0.0000

Data Index: 883604 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.3078. Min Range: -1.3078

Max Act: 0.9908. Min Act: -0.0000

Data Index: 327357 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.0529. Min Act: -0.0000

Data Index: 67148 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.3078. Min Range: -1.3078

Max Act: 1.0554. Min Act: -0.0000

Data Index: 113203 (C4 (Web Text))

Max Activating Token Index: 182