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

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

Neuron 3550 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.7379. Min Act: -0.0000

Data Index: 395987 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.8786. Min Act: -0.0000

Data Index: 559311 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.3687. Min Act: -0.0000

Data Index: 938241 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.0586. Min Act: -0.0000

Data Index: 414357 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.1619. Min Act: -0.0000

Data Index: 933334 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.0502. Min Act: -0.0000

Data Index: 345725 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.8786. Min Range: -3.8786

Max Act: 3.0261. Min Act: -0.0000

Data Index: 595665 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.9846. Min Act: -0.0000

Data Index: 568638 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.9825. Min Act: -0.0000

Data Index: 504410 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.6998. Min Act: -0.0000

Data Index: 146527 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.8058. Min Act: -0.0000

Data Index: 16658 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.9401. Min Act: -0.0000

Data Index: 687054 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.6428. Min Act: -0.0000

Data Index: 870547 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.7825. Min Act: -0.0000

Data Index: 128460 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.8726. Min Act: -0.0000

Data Index: 399391 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.9751. Min Act: -0.0000

Data Index: 593717 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.7828. Min Act: -0.0000

Data Index: 800027 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.6929. Min Act: 0.0000

Data Index: 966518 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.8239. Min Act: -0.0000

Data Index: 931932 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.8786. Min Range: -3.8786

Max Act: 2.6878. Min Act: 0.0000

Data Index: 408148 (C4 (Web Text))

Max Activating Token Index: 107