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

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

Neuron 3828 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: 0.2552. Min Range: -0.2552

Max Act: 0.2503. Min Act: -0.0001

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2552. Min Act: -0.0000

Data Index: 956383 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1897. Min Act: -0.0000

Data Index: 704611 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2044. Min Act: -0.0001

Data Index: 888219 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2017. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2053. Min Act: -0.0000

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1927. Min Act: -0.0001

Data Index: 40427 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1038360 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1320558 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1933. Min Act: -0.0000

Data Index: 417518 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1937. Min Act: -0.0001

Data Index: 516441 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1797. Min Act: -0.0001

Data Index: 533984 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1796. Min Act: -0.0001

Data Index: 969689 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1775. Min Act: -0.0000

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1906. Min Act: -0.0000

Data Index: 365189 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1820. Min Act: -0.0000

Data Index: 608647 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1619. Min Act: -0.0001

Data Index: 198680 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1257649 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1788. Min Act: -0.0001

Data Index: 359339 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1644. Min Act: -0.0000

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 554