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

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

Neuron 3425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2430. Min Act: -0.0000

Data Index: 253896 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2944. Min Act: -0.0000

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1226. Min Act: -0.0000

Data Index: 772829 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1413. Min Act: -0.0000

Data Index: 118630 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1015669 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0295. Min Act: -0.0000

Data Index: 687133 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9985. Min Act: -0.0000

Data Index: 329076 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0981. Min Act: -0.0000

Data Index: 119330 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1280448 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9842. Min Act: -0.0000

Data Index: 440275 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9808. Min Act: -0.0001

Data Index: 17476 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9668. Min Act: -0.0000

Data Index: 91398 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9623. Min Act: -0.0001

Data Index: 575483 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8826. Min Act: -0.0000

Data Index: 130500 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9545. Min Act: -0.0000

Data Index: 651809 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9425. Min Act: -0.0000

Data Index: 367885 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1878 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1073877 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0217. Min Act: -0.0000

Data Index: 372324 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9024. Min Act: -0.0001

Data Index: 751293 (C4 (Web Text))

Max Activating Token Index: 717