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

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

Neuron 4239 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1259. Min Act: -0.0002

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0002

Data Index: 75399 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1232. Min Act: -0.0002

Data Index: 902424 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1029. Min Act: -0.0002

Data Index: 396945 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1153. Min Act: -0.0002

Data Index: 691479 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1175. Min Act: -0.0002

Data Index: 182211 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1018. Min Act: -0.0002

Data Index: 864147 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0973. Min Act: -0.0002

Data Index: 519310 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1140438 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0965. Min Act: -0.0002

Data Index: 158663 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1084634 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1319470 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1172619 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0993. Min Act: -0.0002

Data Index: 754605 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1009. Min Act: -0.0002

Data Index: 181784 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0913. Min Act: -0.0002

Data Index: 909549 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0979. Min Act: -0.0002

Data Index: 585018 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0983. Min Act: -0.0002

Data Index: 210074 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1030. Min Act: -0.0002

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0954. Min Act: -0.0002

Data Index: 722696 (C4 (Web Text))

Max Activating Token Index: 87