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

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

Neuron 3552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.5239. Min Act: -0.0001

Data Index: 1322020 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.3582. Min Act: -0.0001

Data Index: 185324 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2691. Min Act: -0.0002

Data Index: 67601 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2538. Min Act: -0.0001

Data Index: 343559 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1921. Min Act: -0.0001

Data Index: 497690 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2231. Min Act: -0.0001

Data Index: 573267 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2121. Min Act: -0.0001

Data Index: 784264 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1985. Min Act: -0.0001

Data Index: 321161 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2011. Min Act: -0.0002

Data Index: 602814 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2379. Min Act: -0.0001

Data Index: 134273 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.2901. Min Act: -0.0001

Data Index: 330527 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1822. Min Act: -0.0001

Data Index: 1011320 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.0409. Min Act: -0.0002

Data Index: 150948 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1266. Min Act: -0.0001

Data Index: 166722 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.0349. Min Act: -0.0001

Data Index: 657792 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1001. Min Act: -0.0001

Data Index: 830622 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1954. Min Act: -0.0001

Data Index: 821727 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.5239. Min Range: -1.5239

Max Act: 0.9366. Min Act: -0.0001

Data Index: 535247 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.0106. Min Act: -0.0002

Data Index: 802452 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.5239. Min Range: -1.5239

Max Act: 1.1094. Min Act: -0.0001

Data Index: 1042108 (C4 (Web Text))

Max Activating Token Index: 228