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

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

Neuron 2015 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1211024 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6747. Min Act: -0.0000

Data Index: 893965 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6687. Min Act: -0.0000

Data Index: 404255 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6896. Min Act: -0.0000

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6206. Min Act: -0.0000

Data Index: 20082 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6085. Min Act: -0.0000

Data Index: 744348 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1220256 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5888. Min Act: -0.0000

Data Index: 397227 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1199770 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5775. Min Act: -0.0000

Data Index: 558199 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1316740 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1135052 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5501. Min Act: -0.0000

Data Index: 34879 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1014206 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1289806 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4810. Min Act: -0.0000

Data Index: 891134 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5075. Min Act: -0.0000

Data Index: 585644 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4872. Min Act: -0.0000

Data Index: 202396 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.5061. Min Act: -0.0000

Data Index: 749052 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.6896. Min Range: -0.6896

Max Act: 0.4913. Min Act: -0.0000

Data Index: 786020 (C4 (Web Text))

Max Activating Token Index: 744