Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4480 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4776. Min Act: -0.0000

Data Index: 832122 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4831. Min Act: -0.0000

Data Index: 228619 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3707. Min Act: -0.0000

Data Index: 215259 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1022023 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3842. Min Act: -0.0000

Data Index: 996314 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3406. Min Act: -0.0000

Data Index: 783189 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4045. Min Act: -0.0000

Data Index: 576742 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4493. Min Act: -0.0000

Data Index: 225956 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3521. Min Act: -0.0000

Data Index: 344257 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3464. Min Act: -0.0000

Data Index: 428863 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3776. Min Act: -0.0000

Data Index: 199832 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3704. Min Act: -0.0000

Data Index: 604824 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3731. Min Act: -0.0000

Data Index: 742767 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3783. Min Act: -0.0000

Data Index: 763994 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1459458 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1302753 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1346781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1373960 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3404. Min Act: -0.0000

Data Index: 283286 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1364766 (Python Code)

Max Activating Token Index: 990