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

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

Neuron 3090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.9845. Min Act: -0.0000

Data Index: 694148 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.6457. Min Act: -0.0001

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.5784. Min Act: -0.0000

Data Index: 1007994 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1583458 (Python Code)

Max Activating Token Index: 893

Text #4

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4199. Min Act: -0.0000

Data Index: 680941 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4643. Min Act: -0.0001

Data Index: 1488514 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1370334 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1630984 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3534. Min Act: -0.0000

Data Index: 505787 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1641148 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3311. Min Act: -0.0001

Data Index: 1373602 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.4073. Min Act: -0.0001

Data Index: 1607572 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3175. Min Act: -0.0001

Data Index: 1552277 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3743. Min Act: -0.0000

Data Index: 232234 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.2594. Min Act: -0.0000

Data Index: 61044 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1399341 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1544701 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.2832. Min Act: -0.0000

Data Index: 186926 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.1919. Min Act: -0.0000

Data Index: 851603 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.9845. Min Range: -1.9845

Max Act: 1.2428. Min Act: -0.0001

Data Index: 1619698 (Python Code)

Max Activating Token Index: 96