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

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

Neuron 871 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1193861 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.4589. Min Act: -0.0000

Data Index: 568023 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.4204. Min Act: -0.0000

Data Index: 678091 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3243. Min Act: -0.0000

Data Index: 550408 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1303125 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3144. Min Act: -0.0000

Data Index: 32292 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3728. Min Act: -0.0000

Data Index: 917465 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3503. Min Act: -0.0000

Data Index: 637107 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3576. Min Act: -0.0000

Data Index: 1253333 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.2469. Min Act: -0.0000

Data Index: 29397 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1294601 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3256. Min Act: -0.0000

Data Index: 805691 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3124. Min Act: -0.0000

Data Index: 826 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3112. Min Act: -0.0000

Data Index: 376168 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.2412. Min Act: -0.0000

Data Index: 843688 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.2905. Min Act: -0.0000

Data Index: 847459 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3642. Min Act: -0.0000

Data Index: 506178 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1062148 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1017911 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.4589. Min Range: -1.4589

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1157064 (C4 (Web Text))

Max Activating Token Index: 113