Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 490 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.8408. Min Act: -0.0001

Data Index: 612580 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7295. Min Act: -0.0000

Data Index: 401117 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7243. Min Act: -0.0001

Data Index: 623769 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7169. Min Act: -0.0001

Data Index: 813852 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7022. Min Act: -0.0000

Data Index: 331309 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6769. Min Act: -0.0001

Data Index: 487883 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6951. Min Act: -0.0000

Data Index: 733784 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7194. Min Act: -0.0001

Data Index: 1430734 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1133121 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.7066. Min Act: -0.0000

Data Index: 760226 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6755. Min Act: -0.0001

Data Index: 914542 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6966. Min Act: -0.0000

Data Index: 844977 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6507. Min Act: -0.0000

Data Index: 658208 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6713. Min Act: -0.0000

Data Index: 265607 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6448. Min Act: -0.0001

Data Index: 254722 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.6428. Min Act: -0.0000

Data Index: 759549 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5888. Min Act: -0.0000

Data Index: 812769 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5481. Min Act: -0.0001

Data Index: 936542 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5995. Min Act: -0.0001

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.8408. Min Range: -0.8408

Max Act: 0.5982. Min Act: -0.0001

Data Index: 176620 (C4 (Web Text))

Max Activating Token Index: 293