Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2778 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2542. Min Act: -0.0001

Data Index: 68946 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2275. Min Act: -0.0001

Data Index: 769042 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2386. Min Act: -0.0001

Data Index: 162600 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1354079 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2015. Min Act: -0.0001

Data Index: 238020 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1145767 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1881. Min Act: -0.0001

Data Index: 766304 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1868. Min Act: -0.0001

Data Index: 832168 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1825. Min Act: -0.0001

Data Index: 345262 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1831. Min Act: -0.0001

Data Index: 497974 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1130339 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1730. Min Act: -0.0001

Data Index: 481724 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1783. Min Act: -0.0001

Data Index: 788779 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1003224 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1585. Min Act: -0.0001

Data Index: 762888 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1792. Min Act: -0.0001

Data Index: 516500 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1535. Min Act: -0.0001

Data Index: 253832 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1698. Min Act: -0.0001

Data Index: 746836 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1076213 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1689. Min Act: -0.0001

Data Index: 937284 (C4 (Web Text))

Max Activating Token Index: 624