Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2586. Min Act: -0.0003

Data Index: 225108 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2360. Min Act: -0.0003

Data Index: 301214 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2247. Min Act: -0.0003

Data Index: 774887 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2187. Min Act: -0.0003

Data Index: 1318001 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2171. Min Act: -0.0003

Data Index: 1108886 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2085. Min Act: -0.0003

Data Index: 66169 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1983. Min Act: -0.0003

Data Index: 216358 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1874. Min Act: -0.0003

Data Index: 1120762 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1919. Min Act: -0.0003

Data Index: 1057761 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1993. Min Act: -0.0003

Data Index: 431224 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2143. Min Act: -0.0003

Data Index: 597336 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1996. Min Act: -0.0003

Data Index: 651128 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2050. Min Act: -0.0003

Data Index: 703753 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1946. Min Act: -0.0003

Data Index: 466923 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1970. Min Act: -0.0003

Data Index: 1223216 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1930. Min Act: -0.0003

Data Index: 819023 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1854. Min Act: -0.0003

Data Index: 187879 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1778. Min Act: -0.0003

Data Index: 68302 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2101. Min Act: -0.0002

Data Index: 794775 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1877. Min Act: -0.0003

Data Index: 663619 (C4 (Web Text))

Max Activating Token Index: 839