Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1384. Min Act: -0.0001

Data Index: 713977 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1332. Min Act: -0.0001

Data Index: 139402 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1233. Min Act: -0.0001

Data Index: 674328 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1298. Min Act: -0.0001

Data Index: 185859 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1225. Min Act: -0.0001

Data Index: 831113 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1219762 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1063. Min Act: -0.0001

Data Index: 62549 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1269030 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1090. Min Act: -0.0001

Data Index: 862000 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1129242 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1047. Min Act: -0.0001

Data Index: 355546 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1047. Min Act: -0.0001

Data Index: 598055 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1041. Min Act: -0.0001

Data Index: 953894 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1066. Min Act: -0.0001

Data Index: 675083 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1273333 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1054671 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0970. Min Act: -0.0001

Data Index: 434088 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1037. Min Act: -0.0001

Data Index: 107213 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1194919 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.1384. Min Range: -0.1384

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1030461 (C4 (Web Text))

Max Activating Token Index: 833