Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1007 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0195. Min Range: -1.0195

Max Act: 1.0039. Min Act: -0.0001

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.0195. Min Range: -1.0195

Max Act: 1.0195. Min Act: -0.0002

Data Index: 394298 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1046696 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.0195. Min Range: -1.0195

Max Act: 1.0027. Min Act: -0.0002

Data Index: 967431 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9858. Min Act: -0.0001

Data Index: 665747 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9716. Min Act: -0.0001

Data Index: 556361 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8881. Min Act: -0.0002

Data Index: 260508 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8822. Min Act: -0.0002

Data Index: 621724 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9273. Min Act: -0.0001

Data Index: 181546 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9149. Min Act: -0.0001

Data Index: 654389 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8507. Min Act: -0.0002

Data Index: 474562 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1540402 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1287970 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8461. Min Act: -0.0002

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7955. Min Act: -0.0002

Data Index: 492100 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8342. Min Act: -0.0001

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8428. Min Act: -0.0001

Data Index: 1439080 (Python Code)

Max Activating Token Index: 648

Text #17

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1552683 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8194. Min Act: -0.0001

Data Index: 410417 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8210. Min Act: -0.0002

Data Index: 1022674 (C4 (Web Text))

Max Activating Token Index: 951