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

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

Neuron 8 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: 1.1996. Min Range: -1.1996

Max Act: 1.1996. Min Act: -0.0001

Data Index: 452003 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.0675. Min Act: -0.0001

Data Index: 495709 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.0553. Min Act: -0.0001

Data Index: 517053 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.0644. Min Act: -0.0001

Data Index: 1008527 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9904. Min Act: -0.0001

Data Index: 798106 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.0432. Min Act: -0.0001

Data Index: 1287004 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.1996. Min Range: -1.1996

Max Act: 1.0129. Min Act: -0.0001

Data Index: 339340 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1119636 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9269. Min Act: -0.0001

Data Index: 1335811 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9704. Min Act: -0.0001

Data Index: 226179 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9512. Min Act: -0.0001

Data Index: 1197504 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9510. Min Act: -0.0001

Data Index: 778868 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9240. Min Act: -0.0001

Data Index: 88438 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9416. Min Act: -0.0001

Data Index: 220565 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9970. Min Act: -0.0001

Data Index: 552374 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9588. Min Act: -0.0001

Data Index: 370424 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9204. Min Act: -0.0001

Data Index: 1104236 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9152. Min Act: -0.0001

Data Index: 968459 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1195381 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.1996. Min Range: -1.1996

Max Act: 0.9318. Min Act: -0.0001

Data Index: 188939 (C4 (Web Text))

Max Activating Token Index: 908