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

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

Neuron 2993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4425. Min Range: -2.4425

Max Act: 2.4425. Min Act: -0.0000

Data Index: 254176 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 2.4425. Min Range: -2.4425

Max Act: 2.1598. Min Act: -0.0001

Data Index: 825363 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 2.4425. Min Range: -2.4425

Max Act: 2.0992. Min Act: -0.0000

Data Index: 730101 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 2.4425. Min Range: -2.4425

Max Act: 2.1333. Min Act: -0.0001

Data Index: 509006 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 2.4425. Min Range: -2.4425

Max Act: 2.1089. Min Act: -0.0001

Data Index: 481581 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 2.4425. Min Range: -2.4425

Max Act: 2.0436. Min Act: -0.0001

Data Index: 490713 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.9884. Min Act: -0.0001

Data Index: 715222 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.8340. Min Act: -0.0001

Data Index: 285146 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.7660. Min Act: -0.0001

Data Index: 611795 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.8374. Min Act: -0.0000

Data Index: 462298 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.8301. Min Act: -0.0000

Data Index: 651599 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6708. Min Act: -0.0000

Data Index: 710711 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.7572. Min Act: -0.0001

Data Index: 288425 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6342. Min Act: -0.0000

Data Index: 74472 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.7603. Min Act: -0.0000

Data Index: 293585 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6555. Min Act: -0.0001

Data Index: 1167375 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6496. Min Act: -0.0001

Data Index: 348086 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6408. Min Act: -0.0001

Data Index: 159011 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6584. Min Act: -0.0000

Data Index: 821556 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 2.4425. Min Range: -2.4425

Max Act: 1.6126. Min Act: -0.0001

Data Index: 402494 (C4 (Web Text))

Max Activating Token Index: 330