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

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

Neuron 982 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.4266. Min Act: -0.0003

Data Index: 1270434 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.2853. Min Act: -0.0003

Data Index: 1353411 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.2107. Min Act: -0.0003

Data Index: 795092 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.2621. Min Act: -0.0003

Data Index: 33245 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.2809. Min Act: -0.0003

Data Index: 670304 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.1561. Min Act: -0.0003

Data Index: 679154 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.2048. Min Act: -0.0003

Data Index: 22883 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.1719. Min Act: -0.0003

Data Index: 937917 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0575. Min Act: -0.0003

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.1006. Min Act: -0.0003

Data Index: 1030601 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.1327. Min Act: -0.0003

Data Index: 175042 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0911. Min Act: -0.0003

Data Index: 476160 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0545. Min Act: -0.0003

Data Index: 217894 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.1165. Min Act: -0.0003

Data Index: 505646 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.4266. Min Range: -1.4266

Max Act: 0.9861. Min Act: -0.0003

Data Index: 486026 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0382. Min Act: -0.0003

Data Index: 446651 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0032. Min Act: -0.0003

Data Index: 244926 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.1247. Min Act: -0.0003

Data Index: 684596 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0646. Min Act: -0.0003

Data Index: 833929 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.4266. Min Range: -1.4266

Max Act: 1.0597. Min Act: -0.0003

Data Index: 1281602 (C4 (Web Text))

Max Activating Token Index: 401