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

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

Neuron 4017 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1144. Min Act: -0.0001

Data Index: 929428 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1199. Min Act: -0.0001

Data Index: 478073 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0001

Data Index: 516785 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1147084 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1021. Min Act: -0.0001

Data Index: 323639 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1059. Min Act: -0.0001

Data Index: 362566 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1109. Min Act: -0.0001

Data Index: 613200 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1121. Min Act: -0.0001

Data Index: 120822 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1053. Min Act: -0.0001

Data Index: 623307 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1335060 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1013. Min Act: -0.0001

Data Index: 321126 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0952. Min Act: -0.0001

Data Index: 410747 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0859. Min Act: -0.0001

Data Index: 197925 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0967. Min Act: -0.0001

Data Index: 485117 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0969. Min Act: -0.0001

Data Index: 455784 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1054. Min Act: -0.0001

Data Index: 112431 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1157746 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1030924 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0931. Min Act: -0.0001

Data Index: 895547 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1002. Min Act: -0.0001

Data Index: 213281 (C4 (Web Text))

Max Activating Token Index: 539