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

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

Neuron 4600 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: 2.8078. Min Range: -2.8078

Max Act: 2.8078. Min Act: -0.0000

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.7856. Min Act: -0.0000

Data Index: 1259343 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.5111. Min Act: -0.0000

Data Index: 150662 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.3525. Min Act: -0.0000

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.3134. Min Act: -0.0000

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.0644. Min Act: -0.0000

Data Index: 870509 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.0665. Min Act: -0.0000

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.9947. Min Act: -0.0000

Data Index: 1342888 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.8821. Min Act: -0.0000

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.0024. Min Act: -0.0000

Data Index: 915592 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.9844. Min Act: -0.0000

Data Index: 342673 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.9915. Min Act: -0.0000

Data Index: 171397 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1063372 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.9570. Min Act: -0.0000

Data Index: 125344 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 2.8078. Min Range: -2.8078

Max Act: 2.0165. Min Act: -0.0000

Data Index: 140393 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.7995. Min Act: -0.0000

Data Index: 12982 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.8340. Min Act: -0.0000

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.8229. Min Act: -0.0000

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.8156. Min Act: -0.0000

Data Index: 389238 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 2.8078. Min Range: -2.8078

Max Act: 1.9166. Min Act: -0.0000

Data Index: 80284 (C4 (Web Text))

Max Activating Token Index: 603