Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4020 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0734. Min Act: -0.0000

Data Index: 736615 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0000

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1273356 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1237842 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0671. Min Act: -0.0000

Data Index: 406005 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1564608 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0640. Min Act: -0.0000

Data Index: 988847 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0654. Min Act: -0.0001

Data Index: 185670 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0601. Min Act: -0.0001

Data Index: 369387 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1108734 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0624. Min Act: -0.0001

Data Index: 185438 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1222320 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0610. Min Act: -0.0000

Data Index: 71820 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0577. Min Act: -0.0001

Data Index: 747465 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0578. Min Act: -0.0001

Data Index: 977537 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0613. Min Act: -0.0001

Data Index: 246256 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1178861 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0606. Min Act: -0.0001

Data Index: 727922 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1099541 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1186583 (C4 (Web Text))

Max Activating Token Index: 200