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

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

Neuron 979 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.5629. Min Act: -0.0002

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.2966. Min Act: -0.0002

Data Index: 13388 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.2239. Min Act: -0.0002

Data Index: 195766 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.2361. Min Act: -0.0002

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.1965. Min Act: -0.0002

Data Index: 301047 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1204397 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.1024. Min Act: -0.0002

Data Index: 642917 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.1024. Min Act: -0.0002

Data Index: 277714 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0897. Min Act: -0.0002

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0886. Min Act: -0.0002

Data Index: 110337 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1375202 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0539. Min Act: -0.0002

Data Index: 572703 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0533. Min Act: -0.0002

Data Index: 445395 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1163446 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0467. Min Act: -0.0002

Data Index: 486079 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0466. Min Act: -0.0002

Data Index: 546076 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0456. Min Act: -0.0002

Data Index: 597892 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0456. Min Act: -0.0002

Data Index: 720997 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.5629. Min Range: -0.5629

Max Act: 0.0476. Min Act: -0.0002

Data Index: 579766 (C4 (Web Text))

Max Activating Token Index: 35