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

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

Neuron 3411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0299. Min Act: -0.0001

Data Index: 679265 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0304. Min Act: -0.0001

Data Index: 217489 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0281. Min Act: -0.0001

Data Index: 326042 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0205. Min Act: -0.0001

Data Index: 534506 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0194. Min Act: -0.0001

Data Index: 28141 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0163. Min Act: -0.0001

Data Index: 879552 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1358240 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1163423 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1347079 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1105254 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1333039 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0162. Min Act: -0.0001

Data Index: 93950 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0144. Min Act: -0.0001

Data Index: 190461 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0125. Min Act: -0.0001

Data Index: 975162 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0138. Min Act: -0.0001

Data Index: 378254 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1024862 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0132. Min Act: -0.0001

Data Index: 847917 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1335869 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0127. Min Act: -0.0001

Data Index: 674788 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0115. Min Act: -0.0001

Data Index: 398783 (C4 (Web Text))

Max Activating Token Index: 245