Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 122 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1279318 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1096. Min Act: -0.0002

Data Index: 663438 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1060. Min Act: -0.0002

Data Index: 119155 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1029. Min Act: -0.0002

Data Index: 44153 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1088. Min Act: -0.0002

Data Index: 502835 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1068. Min Act: -0.0002

Data Index: 996201 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1041. Min Act: -0.0002

Data Index: 565340 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1322137 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1010. Min Act: -0.0002

Data Index: 325771 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1025. Min Act: -0.0002

Data Index: 977852 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1000. Min Act: -0.0002

Data Index: 469430 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1017. Min Act: -0.0002

Data Index: 289941 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0963. Min Act: -0.0002

Data Index: 425151 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0961. Min Act: -0.0002

Data Index: 190683 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0963. Min Act: -0.0002

Data Index: 641029 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0938. Min Act: -0.0001

Data Index: 430973 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0948. Min Act: -0.0001

Data Index: 818259 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0950. Min Act: -0.0002

Data Index: 236203 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1340423 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0962. Min Act: -0.0002

Data Index: 751378 (C4 (Web Text))

Max Activating Token Index: 812