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

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

Neuron 2298 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.4389. Min Act: -0.0000

Data Index: 852014 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2825. Min Act: -0.0000

Data Index: 136132 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1740. Min Act: -0.0000

Data Index: 947968 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1119. Min Act: -0.0000

Data Index: 9981 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9970. Min Act: -0.0000

Data Index: 46603 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9758. Min Act: -0.0000

Data Index: 464330 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.9588. Min Act: -0.0000

Data Index: 927827 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.8211. Min Act: -0.0000

Data Index: 348395 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.8289. Min Act: -0.0000

Data Index: 974929 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.7510. Min Act: -0.0000

Data Index: 160646 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.7320. Min Act: -0.0000

Data Index: 905274 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.7453. Min Act: -0.0000

Data Index: 870933 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6199. Min Act: -0.0000

Data Index: 37208 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6804. Min Act: -0.0000

Data Index: 673936 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6801. Min Act: -0.0000

Data Index: 151391 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6716. Min Act: -0.0000

Data Index: 372798 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6226. Min Act: -0.0000

Data Index: 224957 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6144. Min Act: -0.0000

Data Index: 841621 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1266251 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 1.4389. Min Range: -1.4389

Max Act: 0.6359. Min Act: -0.0000

Data Index: 747566 (C4 (Web Text))

Max Activating Token Index: 604