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

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

Neuron 681 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: 0.2135. Min Range: -0.2135

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1104530 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1147572 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1320. Min Act: -0.0001

Data Index: 399227 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1311. Min Act: -0.0001

Data Index: 507584 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1351. Min Act: -0.0001

Data Index: 29670 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1321. Min Act: -0.0001

Data Index: 822352 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1213. Min Act: -0.0001

Data Index: 498499 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1332. Min Act: -0.0001

Data Index: 995920 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1058439 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1345274 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1218. Min Act: -0.0001

Data Index: 904566 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1140. Min Act: -0.0001

Data Index: 79921 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1223. Min Act: -0.0001

Data Index: 380157 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1023270 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1109. Min Act: -0.0001

Data Index: 964157 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1067. Min Act: -0.0001

Data Index: 435721 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1110. Min Act: -0.0001

Data Index: 125596 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1050049 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1131. Min Act: -0.0001

Data Index: 606956 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1245524 (C4 (Web Text))

Max Activating Token Index: 1004