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

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

Neuron 2095 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1024. Min Act: -0.0004

Data Index: 505378 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1070. Min Act: -0.0004

Data Index: 14251 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1061. Min Act: -0.0004

Data Index: 1293200 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1041. Min Act: -0.0004

Data Index: 18154 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1101. Min Act: -0.0004

Data Index: 1188632 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1068. Min Act: -0.0004

Data Index: 1123448 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0819. Min Act: -0.0004

Data Index: 472505 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0987. Min Act: -0.0004

Data Index: 1144862 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0946. Min Act: -0.0004

Data Index: 437341 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1034. Min Act: -0.0004

Data Index: 1054968 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1029. Min Act: -0.0004

Data Index: 696484 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1071. Min Act: -0.0004

Data Index: 955026 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0004

Data Index: 842893 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1097. Min Act: -0.0004

Data Index: 754207 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1052. Min Act: -0.0004

Data Index: 727245 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0791. Min Act: -0.0004

Data Index: 742948 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1046. Min Act: -0.0004

Data Index: 1277049 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0912. Min Act: -0.0004

Data Index: 880969 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0973. Min Act: -0.0004

Data Index: 484393 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1003. Min Act: -0.0004

Data Index: 1096673 (C4 (Web Text))

Max Activating Token Index: 611