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

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

Neuron 2551 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: 1.8354. Min Range: -1.8354

Max Act: 1.6441. Min Act: -0.0000

Data Index: 172616 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.8354. Min Act: -0.0000

Data Index: 364758 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6969. Min Act: -0.0000

Data Index: 1344686 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6292. Min Act: -0.0000

Data Index: 575200 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1271349 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6749. Min Act: -0.0000

Data Index: 217760 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5465. Min Act: -0.0000

Data Index: 331935 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6512. Min Act: -0.0000

Data Index: 814930 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5426. Min Act: -0.0000

Data Index: 687726 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5280. Min Act: -0.0000

Data Index: 1053533 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7155. Min Act: -0.0000

Data Index: 424616 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4013. Min Act: -0.0000

Data Index: 344023 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4856. Min Act: -0.0000

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4575. Min Act: -0.0000

Data Index: 958026 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4263. Min Act: -0.0000

Data Index: 256573 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5050. Min Act: -0.0000

Data Index: 59745 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3315. Min Act: -0.0000

Data Index: 338346 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4122. Min Act: -0.0000

Data Index: 45902 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3166. Min Act: -0.0000

Data Index: 452557 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.1910. Min Act: -0.0000

Data Index: 704546 (C4 (Web Text))

Max Activating Token Index: 794