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

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

Neuron 1436 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.5358. Min Act: -0.0000

Data Index: 883329 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.5787. Min Act: -0.0000

Data Index: 119721 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.4282. Min Act: -0.0000

Data Index: 538058 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.3274. Min Act: -0.0000

Data Index: 471429 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.1536. Min Act: -0.0000

Data Index: 725735 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1233712 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.0690. Min Act: -0.0000

Data Index: 331181 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.9640. Min Act: -0.0000

Data Index: 357740 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.9304. Min Act: -0.0000

Data Index: 157003 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.0231. Min Act: -0.0000

Data Index: 733182 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.1359. Min Act: -0.0000

Data Index: 925876 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.0149. Min Act: -0.0000

Data Index: 942660 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.5787. Min Range: -1.5787

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1104282 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.8556. Min Act: -0.0000

Data Index: 60216 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.8696. Min Act: -0.0000

Data Index: 60901 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.9546. Min Act: -0.0000

Data Index: 446779 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1209116 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.9453. Min Act: -0.0000

Data Index: 396974 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.8485. Min Act: -0.0000

Data Index: 813548 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.5787. Min Range: -1.5787

Max Act: 0.8796. Min Act: -0.0000

Data Index: 799235 (C4 (Web Text))

Max Activating Token Index: 91