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

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

Neuron 3851 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.9603. Min Act: -0.0001

Data Index: 65360 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7888. Min Act: -0.0001

Data Index: 725111 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7171. Min Act: -0.0001

Data Index: 657414 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7124. Min Act: -0.0001

Data Index: 971146 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7158. Min Act: -0.0001

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7094. Min Act: -0.0001

Data Index: 1114951 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6152. Min Act: -0.0001

Data Index: 968480 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6307. Min Act: -0.0001

Data Index: 83923 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1143737 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6433. Min Act: -0.0001

Data Index: 734565 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6321. Min Act: -0.0001

Data Index: 77843 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6136. Min Act: -0.0001

Data Index: 1092876 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5411. Min Act: -0.0001

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1141197 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5831. Min Act: -0.0001

Data Index: 391065 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5738. Min Act: -0.0001

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6212. Min Act: -0.0001

Data Index: 522462 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5755. Min Act: -0.0001

Data Index: 301908 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5377. Min Act: -0.0001

Data Index: 97439 (C4 (Web Text))

Max Activating Token Index: 1009