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

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

Neuron 3251 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1196758 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1398. Min Act: -0.0001

Data Index: 969515 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1326. Min Act: -0.0001

Data Index: 619557 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1302. Min Act: -0.0001

Data Index: 600563 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1206. Min Act: -0.0001

Data Index: 824145 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1058267 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1230. Min Act: -0.0001

Data Index: 607798 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1202. Min Act: -0.0001

Data Index: 911128 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1150. Min Act: -0.0000

Data Index: 127264 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1172. Min Act: -0.0001

Data Index: 797786 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1211. Min Act: -0.0001

Data Index: 505751 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1128. Min Act: -0.0000

Data Index: 786787 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1181744 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1132. Min Act: -0.0000

Data Index: 699812 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1121. Min Act: -0.0001

Data Index: 333677 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1301046 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1082. Min Act: -0.0000

Data Index: 953573 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1084. Min Act: -0.0000

Data Index: 10118 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1087. Min Act: -0.0001

Data Index: 280023 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1054. Min Act: -0.0001

Data Index: 558905 (C4 (Web Text))

Max Activating Token Index: 282