Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1247 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3416. Min Act: -0.0000

Data Index: 807428 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.4255. Min Act: -0.0000

Data Index: 940589 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3928. Min Act: -0.0000

Data Index: 805832 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2096. Min Act: -0.0000

Data Index: 153933 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0970. Min Act: -0.0000

Data Index: 219330 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0788. Min Act: -0.0000

Data Index: 154725 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9805. Min Act: -0.0000

Data Index: 849492 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0429. Min Act: -0.0000

Data Index: 457749 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.1038. Min Act: -0.0000

Data Index: 393756 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0077. Min Act: -0.0000

Data Index: 616191 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9146. Min Act: -0.0000

Data Index: 631620 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1341207 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.8991. Min Act: -0.0000

Data Index: 801922 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9868. Min Act: 0.0000

Data Index: 1089211 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9025. Min Act: -0.0000

Data Index: 33300 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.8959. Min Act: -0.0000

Data Index: 68134 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9068. Min Act: -0.0000

Data Index: 446310 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1299765 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.8577. Min Act: -0.0000

Data Index: 996423 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 1.4255. Min Range: -1.4255

Max Act: 0.8609. Min Act: -0.0000

Data Index: 495206 (C4 (Web Text))

Max Activating Token Index: 18