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

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

Neuron 2068 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8836. Min Act: -0.0000

Data Index: 949146 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5897. Min Act: -0.0000

Data Index: 768756 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6182. Min Act: -0.0000

Data Index: 948221 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5625. Min Act: -0.0000

Data Index: 736391 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6375. Min Act: -0.0000

Data Index: 621824 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5964. Min Act: -0.0000

Data Index: 904671 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5640. Min Act: -0.0000

Data Index: 915579 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1150666 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4788. Min Act: -0.0000

Data Index: 667589 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4671. Min Act: -0.0000

Data Index: 388474 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4788. Min Act: -0.0000

Data Index: 420345 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4556. Min Act: -0.0000

Data Index: 3540 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4397. Min Act: -0.0000

Data Index: 605511 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4872. Min Act: -0.0000

Data Index: 37358 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4211. Min Act: -0.0000

Data Index: 712398 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4299. Min Act: -0.0000

Data Index: 470063 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4688. Min Act: -0.0000

Data Index: 564963 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1153562 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.3497. Min Act: -0.0000

Data Index: 23349 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.3969. Min Act: -0.0000

Data Index: 548669 (C4 (Web Text))

Max Activating Token Index: 968