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

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

Neuron 2474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.4907. Min Act: -0.0000

Data Index: 517381 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1282023 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1085346 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.1476. Min Act: -0.0000

Data Index: 723765 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0939. Min Act: -0.0000

Data Index: 839617 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1028243 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.2084. Min Act: -0.0000

Data Index: 290520 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.1124. Min Act: -0.0000

Data Index: 699478 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1115102 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0928. Min Act: -0.0000

Data Index: 850857 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.1678. Min Act: -0.0000

Data Index: 941363 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.1145. Min Act: -0.0000

Data Index: 137607 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0579. Min Act: -0.0000

Data Index: 569645 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.4907. Min Range: -1.4907

Max Act: 0.9785. Min Act: -0.0000

Data Index: 479366 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0526. Min Act: -0.0000

Data Index: 496119 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1247194 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0987. Min Act: -0.0000

Data Index: 848367 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0998. Min Act: -0.0000

Data Index: 228454 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.4907. Min Range: -1.4907

Max Act: 1.0380. Min Act: -0.0000

Data Index: 466694 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.4907. Min Range: -1.4907

Max Act: 0.9838. Min Act: -0.0000

Data Index: 194080 (C4 (Web Text))

Max Activating Token Index: 485