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

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

Neuron 405 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.5354. Min Act: -0.0000

Data Index: 81397 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.5386. Min Act: -0.0000

Data Index: 575376 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.5419. Min Act: -0.0000

Data Index: 309916 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.5189. Min Act: -0.0000

Data Index: 876403 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1358063 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4949. Min Act: -0.0000

Data Index: 88114 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4752. Min Act: -0.0000

Data Index: 181353 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4829. Min Act: -0.0000

Data Index: 793853 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1213009 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4480. Min Act: -0.0000

Data Index: 835798 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4355. Min Act: -0.0000

Data Index: 252617 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4368. Min Act: -0.0000

Data Index: 196834 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1319867 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1114000 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4001. Min Act: -0.0000

Data Index: 963153 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.3200. Min Act: -0.0000

Data Index: 31568 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.3253. Min Act: -0.0000

Data Index: 175802 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.2624. Min Act: -0.0000

Data Index: 785977 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.2567. Min Act: -0.0000

Data Index: 712342 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1228330 (C4 (Web Text))

Max Activating Token Index: 386