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

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

Neuron 242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2289. Min Act: -0.0000

Data Index: 286764 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2864. Min Act: -0.0000

Data Index: 855391 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1277483 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1203087 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1112990 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.1534. Min Act: -0.0000

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0083. Min Act: -0.0000

Data Index: 518309 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0491. Min Act: -0.0000

Data Index: 537545 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0539. Min Act: -0.0000

Data Index: 234495 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9876. Min Act: -0.0000

Data Index: 306826 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0372. Min Act: -0.0000

Data Index: 237968 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.2908. Min Range: -1.2908

Max Act: 1.0331. Min Act: -0.0000

Data Index: 958904 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.8929. Min Act: -0.0000

Data Index: 676079 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9415. Min Act: -0.0000

Data Index: 939427 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9417. Min Act: -0.0000

Data Index: 868157 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.8965. Min Act: -0.0000

Data Index: 392585 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1353874 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.9306. Min Act: -0.0000

Data Index: 327854 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.8475. Min Act: -0.0000

Data Index: 66289 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 1.2908. Min Range: -1.2908

Max Act: 0.8258. Min Act: -0.0000

Data Index: 374104 (C4 (Web Text))

Max Activating Token Index: 184