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

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

Neuron 1603 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.8119. Min Act: -0.0001

Data Index: 177520 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.5942. Min Act: -0.0000

Data Index: 108566 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.5651. Min Act: -0.0000

Data Index: 368510 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.2929. Min Act: -0.0000

Data Index: 969577 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.3826. Min Act: -0.0000

Data Index: 1108567 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.2476. Min Act: -0.0000

Data Index: 725921 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.2459. Min Act: -0.0000

Data Index: 189190 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.2379. Min Act: -0.0000

Data Index: 254803 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.1076. Min Act: -0.0000

Data Index: 737041 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.9855. Min Act: -0.0000

Data Index: 454595 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.0267. Min Act: -0.0001

Data Index: 397996 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.8119. Min Range: -2.8119

Max Act: 2.0091. Min Act: -0.0000

Data Index: 1149924 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.9816. Min Act: -0.0000

Data Index: 675677 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.9626. Min Act: -0.0001

Data Index: 480812 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.9344. Min Act: -0.0000

Data Index: 832459 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.9308. Min Act: -0.0000

Data Index: 688889 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.9010. Min Act: -0.0000

Data Index: 947125 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.7717. Min Act: -0.0000

Data Index: 394255 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.8600. Min Act: -0.0000

Data Index: 1240877 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 2.8119. Min Range: -2.8119

Max Act: 1.8140. Min Act: -0.0001

Data Index: 1246222 (C4 (Web Text))

Max Activating Token Index: 289