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

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

Neuron 2405 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0001

Data Index: 1468439 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1496988 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4200. Min Act: -0.0001

Data Index: 470952 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1090607 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3897. Min Act: -0.0001

Data Index: 452716 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4422. Min Act: -0.0000

Data Index: 55893 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4238. Min Act: -0.0001

Data Index: 881101 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1459528 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3824. Min Act: -0.0001

Data Index: 259154 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4520. Min Act: -0.0000

Data Index: 35559 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3932. Min Act: -0.0001

Data Index: 660003 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1238189 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1391065 (Python Code)

Max Activating Token Index: 165

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3844. Min Act: -0.0001

Data Index: 1423330 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1634201 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3585. Min Act: -0.0001

Data Index: 203608 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1379550 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3575. Min Act: -0.0001

Data Index: 1251683 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4054. Min Act: -0.0000

Data Index: 227682 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4031. Min Act: -0.0000

Data Index: 421950 (C4 (Web Text))

Max Activating Token Index: 692