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

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

Neuron 881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0289. Min Range: -8.0289

Max Act: 8.0289. Min Act: -0.0000

Data Index: 291524 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 8.0289. Min Range: -8.0289

Max Act: 7.2780. Min Act: -0.0000

Data Index: 273645 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 8.0289. Min Range: -8.0289

Max Act: 7.3348. Min Act: -0.0000

Data Index: 626012 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 8.0289. Min Range: -8.0289

Max Act: 7.1550. Min Act: -0.0000

Data Index: 719938 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.7662. Min Act: -0.0000

Data Index: 37228 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.9122. Min Act: -0.0000

Data Index: 1328638 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.7220. Min Act: -0.0000

Data Index: 781876 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.8568. Min Act: -0.0000

Data Index: 102358 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.8371. Min Act: -0.0000

Data Index: 958852 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 8.0289. Min Range: -8.0289

Max Act: 7.0332. Min Act: -0.0000

Data Index: 857463 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.8376. Min Act: -0.0000

Data Index: 173210 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.9599. Min Act: -0.0000

Data Index: 1159848 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.8437. Min Act: -0.0000

Data Index: 1036318 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.2420. Min Act: -0.0000

Data Index: 157893 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.2094. Min Act: -0.0000

Data Index: 735787 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.2483. Min Act: -0.0000

Data Index: 366340 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.4991. Min Act: -0.0000

Data Index: 1089162 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.6577. Min Act: -0.0000

Data Index: 837570 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.2935. Min Act: -0.0000

Data Index: 1168073 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 8.0289. Min Range: -8.0289

Max Act: 6.6177. Min Act: -0.0000

Data Index: 751020 (C4 (Web Text))

Max Activating Token Index: 998