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

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

Neuron 9 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.8450. Min Act: 0.0001

Data Index: 1022050 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.7690. Min Act: -0.0000

Data Index: 842996 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.7515. Min Act: 0.0001

Data Index: 466382 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6851. Min Act: -0.0000

Data Index: 18609 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1212223 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6578. Min Act: 0.0001

Data Index: 1209106 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6351. Min Act: 0.0000

Data Index: 590338 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6004. Min Act: -0.0000

Data Index: 627822 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6192. Min Act: 0.0000

Data Index: 591753 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1034979 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1207090 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5775. Min Act: -0.0000

Data Index: 908561 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5875. Min Act: -0.0000

Data Index: 688186 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5662. Min Act: -0.0000

Data Index: 120767 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5643. Min Act: 0.0001

Data Index: 771723 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1357883 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5557. Min Act: -0.0000

Data Index: 10071 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5717. Min Act: 0.0000

Data Index: 26853 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1102203 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.8450. Min Range: -0.8450

Max Act: 0.5173. Min Act: -0.0000

Data Index: 241314 (C4 (Web Text))

Max Activating Token Index: 209