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

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

Neuron 1040 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1266352 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3460. Min Act: -0.0000

Data Index: 727354 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1330036 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3014. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3029. Min Act: -0.0000

Data Index: 880216 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1149452 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2745. Min Act: -0.0000

Data Index: 147023 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2243. Min Act: -0.0000

Data Index: 816473 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2373. Min Act: -0.0000

Data Index: 14487 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2309. Min Act: -0.0000

Data Index: 531703 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1002358 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2192. Min Act: -0.0000

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2390. Min Act: -0.0000

Data Index: 349027 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1892. Min Act: -0.0000

Data Index: 699141 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2278. Min Act: -0.0000

Data Index: 209124 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.1773. Min Act: -0.0000

Data Index: 443549 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2162. Min Act: -0.0000

Data Index: 268587 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2236. Min Act: -0.0000

Data Index: 655411 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2449. Min Act: -0.0000

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1004939 (C4 (Web Text))

Max Activating Token Index: 871