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

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

Neuron 4983 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: 1.1442. Min Range: -1.1442

Max Act: 1.1195. Min Act: -0.0000

Data Index: 459202 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.0506. Min Act: -0.0000

Data Index: 317623 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.1442. Min Act: -0.0000

Data Index: 206537 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1247695 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1287827 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.1233. Min Act: -0.0000

Data Index: 166791 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.0496. Min Act: -0.0000

Data Index: 714729 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.0873. Min Act: -0.0000

Data Index: 357280 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1004097 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1339801 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.0443. Min Act: -0.0000

Data Index: 102189 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1046950 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9116. Min Act: -0.0000

Data Index: 492940 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9893. Min Act: -0.0000

Data Index: 61571 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9257. Min Act: -0.0000

Data Index: 400941 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1073249 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1070944 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9361. Min Act: -0.0000

Data Index: 64491 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1019826 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9099. Min Act: -0.0000

Data Index: 810359 (C4 (Web Text))

Max Activating Token Index: 304