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

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

Neuron 2220 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.7976. Min Act: -0.0000

Data Index: 757770 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.5560. Min Act: -0.0000

Data Index: 986692 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.5761. Min Act: -0.0000

Data Index: 916041 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.3468. Min Act: -0.0000

Data Index: 635348 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1165439 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.4093. Min Act: -0.0000

Data Index: 781115 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1154334 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1024260 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.4671. Min Act: -0.0000

Data Index: 873961 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.2663. Min Act: -0.0001

Data Index: 108632 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.2865. Min Act: -0.0000

Data Index: 869877 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.2295. Min Act: -0.0000

Data Index: 766888 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1969. Min Act: -0.0001

Data Index: 328782 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1257368 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1267125 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.2151. Min Act: -0.0000

Data Index: 974844 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1499. Min Act: -0.0000

Data Index: 720998 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1795. Min Act: -0.0000

Data Index: 737888 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1803. Min Act: -0.0000

Data Index: 40511 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.7976. Min Range: -1.7976

Max Act: 1.1775. Min Act: -0.0000

Data Index: 7631 (C4 (Web Text))

Max Activating Token Index: 427