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

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

Neuron 3461 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0000

Data Index: 649729 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1512. Min Act: -0.0000

Data Index: 736631 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1009072 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1247. Min Act: -0.0001

Data Index: 668610 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1186. Min Act: -0.0000

Data Index: 388619 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1211. Min Act: -0.0000

Data Index: 949793 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1123. Min Act: -0.0000

Data Index: 290525 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0999. Min Act: -0.0000

Data Index: 459280 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0949. Min Act: -0.0000

Data Index: 142396 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1127. Min Act: -0.0001

Data Index: 786716 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1328162 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1581901 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0919. Min Act: -0.0000

Data Index: 257703 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0984. Min Act: -0.0000

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0912. Min Act: -0.0001

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0877. Min Act: -0.0000

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0906. Min Act: -0.0000

Data Index: 905691 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0886. Min Act: -0.0000

Data Index: 471469 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0965. Min Act: -0.0000

Data Index: 530634 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0758. Min Act: -0.0000

Data Index: 959795 (C4 (Web Text))

Max Activating Token Index: 270