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

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

Neuron 5058 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: 0.6639. Min Range: -0.6639

Max Act: 0.6540. Min Act: -0.0000

Data Index: 990150 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6639. Min Act: -0.0000

Data Index: 241028 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6055. Min Act: -0.0000

Data Index: 433547 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5524. Min Act: -0.0001

Data Index: 613854 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5704. Min Act: -0.0000

Data Index: 847963 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5834. Min Act: -0.0000

Data Index: 966926 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5139. Min Act: -0.0000

Data Index: 772931 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5567. Min Act: -0.0000

Data Index: 629540 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5181. Min Act: -0.0000

Data Index: 799488 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5215. Min Act: -0.0000

Data Index: 564496 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5067. Min Act: -0.0000

Data Index: 843245 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4884. Min Act: -0.0000

Data Index: 620830 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5566. Min Act: -0.0000

Data Index: 16155 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5070. Min Act: -0.0000

Data Index: 922033 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4831. Min Act: -0.0000

Data Index: 950662 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5086. Min Act: -0.0000

Data Index: 480294 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4539. Min Act: -0.0000

Data Index: 118985 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4779. Min Act: -0.0000

Data Index: 668856 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1012827 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4281. Min Act: -0.0000

Data Index: 52940 (C4 (Web Text))

Max Activating Token Index: 63