Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 756 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.5136. Min Act: -0.0001

Data Index: 436066 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4329. Min Act: -0.0001

Data Index: 829602 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4871. Min Act: -0.0001

Data Index: 813556 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4576. Min Act: -0.0001

Data Index: 958450 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4575. Min Act: -0.0001

Data Index: 1131194 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4659. Min Act: -0.0001

Data Index: 449939 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4459. Min Act: -0.0001

Data Index: 309936 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4276. Min Act: -0.0001

Data Index: 1358569 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4522. Min Act: -0.0001

Data Index: 769748 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4312. Min Act: -0.0001

Data Index: 139476 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4549. Min Act: -0.0001

Data Index: 210422 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4376. Min Act: -0.0001

Data Index: 125928 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4206. Min Act: -0.0001

Data Index: 376576 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4317. Min Act: -0.0001

Data Index: 971682 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4246. Min Act: -0.0001

Data Index: 580160 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4082. Min Act: -0.0001

Data Index: 126865 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4249. Min Act: -0.0001

Data Index: 926530 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1102142 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.4067. Min Act: -0.0001

Data Index: 1014522 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.5136. Min Range: -0.5136

Max Act: 0.3976. Min Act: -0.0001

Data Index: 962955 (C4 (Web Text))

Max Activating Token Index: 498