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

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

Neuron 915 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1464. Min Act: -0.0001

Data Index: 74226 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1350. Min Act: -0.0001

Data Index: 447500 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1484. Min Act: -0.0001

Data Index: 556106 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1244. Min Act: -0.0001

Data Index: 950768 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1220894 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1225. Min Act: -0.0001

Data Index: 905989 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1227. Min Act: -0.0001

Data Index: 375107 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1131761 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1133. Min Act: -0.0001

Data Index: 320350 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1257830 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1119215 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1076. Min Act: -0.0001

Data Index: 895666 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1062. Min Act: -0.0001

Data Index: 472177 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1007. Min Act: -0.0001

Data Index: 910818 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1094526 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1111149 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1053. Min Act: -0.0001

Data Index: 292670 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1007. Min Act: -0.0001

Data Index: 604620 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0929. Min Act: -0.0001

Data Index: 900709 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.0948. Min Act: -0.0001

Data Index: 669113 (C4 (Web Text))

Max Activating Token Index: 41