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

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

Neuron 4099 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1103883 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6134. Min Act: -0.0000

Data Index: 777543 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6076. Min Act: -0.0000

Data Index: 720084 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1094323 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5087. Min Act: -0.0000

Data Index: 254742 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4669. Min Act: -0.0000

Data Index: 450503 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4368. Min Act: -0.0000

Data Index: 270270 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4077. Min Act: 0.0001

Data Index: 1112604 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4057. Min Act: -0.0000

Data Index: 79835 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4012. Min Act: -0.0000

Data Index: 922289 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3839. Min Act: 0.0000

Data Index: 823451 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3966. Min Act: -0.0000

Data Index: 541904 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3952. Min Act: -0.0000

Data Index: 763024 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.4016. Min Act: -0.0000

Data Index: 717219 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3613. Min Act: -0.0000

Data Index: 537898 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3923. Min Act: -0.0000

Data Index: 130912 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1041082 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3754. Min Act: -0.0000

Data Index: 950177 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3668. Min Act: -0.0000

Data Index: 330456 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1284727 (C4 (Web Text))

Max Activating Token Index: 874