Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 299 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3813. Min Act: -0.0001

Data Index: 452230 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3006. Min Act: -0.0001

Data Index: 1227322 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.4490. Min Act: -0.0001

Data Index: 379655 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.4185. Min Act: -0.0001

Data Index: 632046 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3351. Min Act: -0.0001

Data Index: 1353069 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3218. Min Act: -0.0001

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1786. Min Act: -0.0001

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.3146. Min Act: -0.0001

Data Index: 64718 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.0823. Min Act: -0.0001

Data Index: 758764 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.0885. Min Act: -0.0001

Data Index: 799774 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 3.4490. Min Range: -3.4490

Max Act: 2.9972. Min Act: -0.0001

Data Index: 461254 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1947. Min Act: -0.0001

Data Index: 315198 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1654. Min Act: -0.0001

Data Index: 905449 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1896. Min Act: -0.0001

Data Index: 965885 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.2539. Min Act: -0.0001

Data Index: 1307424 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.0816. Min Act: -0.0001

Data Index: 820591 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1432. Min Act: -0.0001

Data Index: 1121518 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1199. Min Act: -0.0001

Data Index: 962160 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1034. Min Act: -0.0001

Data Index: 976538 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 3.4490. Min Range: -3.4490

Max Act: 3.1174. Min Act: -0.0001

Data Index: 999028 (C4 (Web Text))

Max Activating Token Index: 417