Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2407 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2349. Min Act: -0.0004

Data Index: 715878 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2217. Min Act: -0.0004

Data Index: 566693 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2091. Min Act: -0.0004

Data Index: 1089985 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1976. Min Act: -0.0004

Data Index: 1088683 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2032. Min Act: -0.0004

Data Index: 312260 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1691. Min Act: -0.0004

Data Index: 97392 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2053. Min Act: -0.0004

Data Index: 418406 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.2055. Min Act: -0.0004

Data Index: 1096177 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1239. Min Act: -0.0004

Data Index: 1003445 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1902. Min Act: -0.0004

Data Index: 658947 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1872. Min Act: -0.0004

Data Index: 204436 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1938. Min Act: -0.0004

Data Index: 185706 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1922. Min Act: -0.0004

Data Index: 697077 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1844. Min Act: -0.0004

Data Index: 451237 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1905. Min Act: -0.0004

Data Index: 579069 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1905. Min Act: -0.0004

Data Index: 181442 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1780. Min Act: -0.0004

Data Index: 814409 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1692. Min Act: -0.0004

Data Index: 1246780 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1891. Min Act: -0.0004

Data Index: 838999 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.2349. Min Range: -0.2349

Max Act: 0.1951. Min Act: -0.0004

Data Index: 888303 (C4 (Web Text))

Max Activating Token Index: 41