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

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

Neuron 715 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7239. Min Range: -2.7239

Max Act: 2.7239. Min Act: -0.0000

Data Index: 1275803 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 2.7239. Min Range: -2.7239

Max Act: 2.3353. Min Act: -0.0000

Data Index: 233933 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 2.7239. Min Range: -2.7239

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1567176 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 2.7239. Min Range: -2.7239

Max Act: 2.1105. Min Act: -0.0000

Data Index: 686181 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.8383. Min Act: -0.0000

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.8805. Min Act: -0.0000

Data Index: 1589301 (Python Code)

Max Activating Token Index: 525

Text #6

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.8530. Min Act: -0.0000

Data Index: 712055 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.9338. Min Act: -0.0000

Data Index: 121963 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.6801. Min Act: -0.0000

Data Index: 157836 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1548815 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5251. Min Act: -0.0000

Data Index: 401837 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5718. Min Act: -0.0000

Data Index: 844235 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5670. Min Act: -0.0000

Data Index: 1227138 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.4165. Min Act: -0.0000

Data Index: 211901 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5430. Min Act: -0.0000

Data Index: 640845 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5439. Min Act: -0.0000

Data Index: 481516 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.7517. Min Act: -0.0000

Data Index: 828449 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.4385. Min Act: -0.0000

Data Index: 153381 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.5672. Min Act: -0.0000

Data Index: 303775 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 2.7239. Min Range: -2.7239

Max Act: 1.4596. Min Act: -0.0000

Data Index: 1163178 (C4 (Web Text))

Max Activating Token Index: 694