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

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

Neuron 2977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.7482. Min Act: -0.0000

Data Index: 800630 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.6293. Min Act: -0.0000

Data Index: 227162 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.5392. Min Act: -0.0000

Data Index: 73641 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1357455 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.6163. Min Act: -0.0000

Data Index: 828619 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.6123. Min Act: -0.0001

Data Index: 382940 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.5281. Min Act: -0.0000

Data Index: 501329 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.5409. Min Act: -0.0000

Data Index: 500250 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4702. Min Act: -0.0000

Data Index: 154164 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4708. Min Act: -0.0000

Data Index: 68649 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.6010. Min Act: -0.0000

Data Index: 125996 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1041849 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4911. Min Act: -0.0001

Data Index: 584093 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4880. Min Act: -0.0000

Data Index: 110746 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4771. Min Act: -0.0000

Data Index: 48682 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4210. Min Act: -0.0000

Data Index: 580382 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.5415. Min Act: -0.0000

Data Index: 249571 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4968. Min Act: -0.0000

Data Index: 813351 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4639. Min Act: -0.0000

Data Index: 599138 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.7482. Min Range: -1.7482

Max Act: 1.4075. Min Act: -0.0000

Data Index: 458289 (C4 (Web Text))

Max Activating Token Index: 322