Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0000

Data Index: 998153 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1164234 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1276168 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1046. Min Act: -0.0000

Data Index: 853010 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1084. Min Act: -0.0000

Data Index: 446009 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1065. Min Act: -0.0000

Data Index: 599367 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1288500 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1022. Min Act: -0.0000

Data Index: 15958 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0962. Min Act: -0.0000

Data Index: 430391 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0942. Min Act: -0.0000

Data Index: 744885 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0967. Min Act: -0.0000

Data Index: 351254 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1077475 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0921. Min Act: -0.0000

Data Index: 216070 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0829. Min Act: -0.0000

Data Index: 110005 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0841. Min Act: -0.0000

Data Index: 226762 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0882. Min Act: -0.0000

Data Index: 620671 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1252906 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0841. Min Act: -0.0000

Data Index: 176593 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0802. Min Act: -0.0000

Data Index: 425829 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0843. Min Act: -0.0000

Data Index: 804971 (C4 (Web Text))

Max Activating Token Index: 487