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

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

Neuron 2121 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.8905. Min Act: -0.0001

Data Index: 31313 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.5377. Min Act: -0.0001

Data Index: 341247 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.6881. Min Act: -0.0001

Data Index: 974307 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.5698. Min Act: -0.0001

Data Index: 358680 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.3753. Min Act: -0.0001

Data Index: 1140064 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.3550. Min Act: -0.0001

Data Index: 44113 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.2296. Min Act: -0.0001

Data Index: 1349157 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.2273. Min Act: -0.0001

Data Index: 38113 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1578. Min Act: -0.0001

Data Index: 509817 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.2338. Min Act: -0.0001

Data Index: 460408 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1264. Min Act: -0.0001

Data Index: 910459 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.2139. Min Act: -0.0001

Data Index: 825112 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.2539. Min Act: -0.0001

Data Index: 586712 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1751. Min Act: -0.0001

Data Index: 81901 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1726. Min Act: -0.0001

Data Index: 515962 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1487. Min Act: -0.0001

Data Index: 1335623 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1564. Min Act: -0.0001

Data Index: 304830 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.1045. Min Act: -0.0001

Data Index: 1117154 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.0346. Min Act: -0.0001

Data Index: 1193114 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 1.8905. Min Range: -1.8905

Max Act: 1.0871. Min Act: -0.0001

Data Index: 655857 (C4 (Web Text))

Max Activating Token Index: 70