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

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

Neuron 4236 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.7369. Min Act: -0.0000

Data Index: 649916 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.7097. Min Act: -0.0000

Data Index: 237269 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6578. Min Act: -0.0000

Data Index: 915822 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.6333. Min Act: -0.0000

Data Index: 618628 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5303. Min Act: -0.0000

Data Index: 879674 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1196703 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5337. Min Act: -0.0000

Data Index: 96040 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4820. Min Act: -0.0000

Data Index: 90600 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4964. Min Act: -0.0000

Data Index: 748974 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4940. Min Act: -0.0000

Data Index: 291715 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5081. Min Act: -0.0000

Data Index: 831459 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4794. Min Act: -0.0000

Data Index: 961708 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.5137. Min Act: -0.0000

Data Index: 440635 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4399. Min Act: -0.0000

Data Index: 563485 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4388. Min Act: -0.0000

Data Index: 350128 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4394. Min Act: -0.0000

Data Index: 617735 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1140897 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4581. Min Act: -0.0000

Data Index: 132902 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1157317 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.7369. Min Range: -0.7369

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1053742 (C4 (Web Text))

Max Activating Token Index: 732