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

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

Neuron 1014 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0002

Data Index: 477888 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1231345 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1255277 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0472. Min Act: -0.0002

Data Index: 455880 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0546. Min Act: -0.0002

Data Index: 174182 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0480. Min Act: -0.0002

Data Index: 613524 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0472. Min Act: -0.0002

Data Index: 572669 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0485. Min Act: -0.0002

Data Index: 147168 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1110994 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1310695 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0457. Min Act: -0.0002

Data Index: 15257 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0503. Min Act: -0.0002

Data Index: 355388 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0454. Min Act: -0.0002

Data Index: 768265 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0475. Min Act: -0.0002

Data Index: 979047 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0468. Min Act: -0.0002

Data Index: 590046 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1196582 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0462. Min Act: -0.0002

Data Index: 954607 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0453. Min Act: -0.0002

Data Index: 646930 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1257020 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0455. Min Act: -0.0002

Data Index: 170798 (C4 (Web Text))

Max Activating Token Index: 333