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

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

Neuron 2931 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1250562 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1098. Min Act: -0.0001

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0969. Min Act: -0.0001

Data Index: 899849 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1289216 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1031. Min Act: -0.0001

Data Index: 104557 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0001

Data Index: 853939 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0997. Min Act: -0.0001

Data Index: 523361 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1325591 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1346583 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0757. Min Act: -0.0001

Data Index: 762829 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0758. Min Act: -0.0001

Data Index: 270879 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1054043 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0821. Min Act: -0.0001

Data Index: 923371 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1637646 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0785. Min Act: -0.0001

Data Index: 64437 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0783. Min Act: -0.0001

Data Index: 76302 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0794. Min Act: -0.0001

Data Index: 180558 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0810. Min Act: -0.0001

Data Index: 128324 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0774. Min Act: -0.0001

Data Index: 370442 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0732. Min Act: -0.0001

Data Index: 594495 (C4 (Web Text))

Max Activating Token Index: 864