Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5310 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9608. Min Act: -0.0001

Data Index: 492551 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9355. Min Act: -0.0001

Data Index: 775898 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.2072. Min Range: -1.2072

Max Act: 1.2072. Min Act: -0.0001

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9122. Min Act: -0.0001

Data Index: 571877 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1235429 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9364. Min Act: -0.0001

Data Index: 1351297 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8864. Min Act: -0.0001

Data Index: 793442 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8978. Min Act: -0.0002

Data Index: 15211 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8976. Min Act: -0.0001

Data Index: 1045058 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8794. Min Act: -0.0001

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8765. Min Act: -0.0001

Data Index: 253981 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8996. Min Act: -0.0001

Data Index: 1279820 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9191. Min Act: -0.0001

Data Index: 196392 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1111808 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.7603. Min Act: -0.0001

Data Index: 157641 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8576. Min Act: -0.0001

Data Index: 20145 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.8449. Min Act: -0.0001

Data Index: 503095 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.7884. Min Act: -0.0001

Data Index: 781946 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.7826. Min Act: -0.0001

Data Index: 812447 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.2072. Min Range: -1.2072

Max Act: 0.7834. Min Act: -0.0001

Data Index: 906084 (C4 (Web Text))

Max Activating Token Index: 942