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

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

Neuron 2176 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: 0.5541. Min Range: -0.5541

Max Act: 0.5541. Min Act: -0.0000

Data Index: 959964 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4547. Min Act: -0.0000

Data Index: 159648 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4681. Min Act: -0.0000

Data Index: 580098 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1218712 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4631. Min Act: -0.0000

Data Index: 787658 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4556. Min Act: -0.0000

Data Index: 529874 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4320. Min Act: 0.0000

Data Index: 1051499 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4216. Min Act: 0.0000

Data Index: 1053116 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4595. Min Act: -0.0000

Data Index: 324060 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1155165 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4121. Min Act: -0.0000

Data Index: 672913 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4191. Min Act: -0.0000

Data Index: 346611 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4155. Min Act: 0.0001

Data Index: 1218086 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1227287 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3988. Min Act: -0.0000

Data Index: 268122 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1301242 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4214. Min Act: 0.0002

Data Index: 923621 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4205. Min Act: -0.0000

Data Index: 7265 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4010. Min Act: 0.0000

Data Index: 679877 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3985. Min Act: -0.0000

Data Index: 554478 (C4 (Web Text))

Max Activating Token Index: 853