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

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

Neuron 1961 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.8531. Min Act: -0.0000

Data Index: 672438 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.9005. Min Act: -0.0000

Data Index: 857585 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1333398 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.3968. Min Act: -0.0000

Data Index: 1633113 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.2178. Min Act: -0.0000

Data Index: 1497751 (Python Code)

Max Activating Token Index: 553

Text #5

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1271328 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9822. Min Act: -0.0000

Data Index: 306541 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0460. Min Act: -0.0000

Data Index: 884882 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0374. Min Act: -0.0000

Data Index: 1200588 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9838. Min Act: -0.0000

Data Index: 637828 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.8836. Min Act: -0.0000

Data Index: 416895 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.8428. Min Act: -0.0000

Data Index: 686950 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.9608. Min Act: -0.0000

Data Index: 415487 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.8269. Min Act: -0.0000

Data Index: 567970 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 2.9005. Min Range: -2.9005

Max Act: 2.0262. Min Act: -0.0000

Data Index: 591677 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1058362 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.7987. Min Act: -0.0000

Data Index: 1325299 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.8023. Min Act: -0.0000

Data Index: 815242 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1090193 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 2.9005. Min Range: -2.9005

Max Act: 1.8696. Min Act: -0.0000

Data Index: 942934 (C4 (Web Text))

Max Activating Token Index: 116