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

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

Neuron 340 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1443. Min Act: -0.0000

Data Index: 694326 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1430. Min Act: -0.0000

Data Index: 807516 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1392. Min Act: -0.0000

Data Index: 761239 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1229187 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1364. Min Act: -0.0000

Data Index: 836076 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1284. Min Act: -0.0000

Data Index: 887640 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1220. Min Act: -0.0000

Data Index: 179123 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1209. Min Act: -0.0000

Data Index: 485681 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1133. Min Act: -0.0000

Data Index: 791803 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1011979 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1103. Min Act: -0.0000

Data Index: 215438 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1085. Min Act: -0.0000

Data Index: 925737 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1066. Min Act: -0.0000

Data Index: 831706 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1212658 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1044. Min Act: -0.0000

Data Index: 689596 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1050. Min Act: -0.0000

Data Index: 242760 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1180127 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1029. Min Act: -0.0000

Data Index: 266099 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1027. Min Act: -0.0000

Data Index: 488357 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1029. Min Act: -0.0000

Data Index: 541725 (C4 (Web Text))

Max Activating Token Index: 160