Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.4570. Min Range: -7.4570

Max Act: 7.4570. Min Act: -0.0000

Data Index: 1262358 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.9746. Min Act: -0.0000

Data Index: 1166824 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.5817. Min Act: -0.0000

Data Index: 237921 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.5370. Min Act: -0.0000

Data Index: 158506 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.5356. Min Act: -0.0000

Data Index: 355698 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.7019. Min Act: -0.0000

Data Index: 1071490 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.7090. Min Act: -0.0000

Data Index: 1247157 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.3647. Min Act: -0.0000

Data Index: 1150162 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.2193. Min Act: -0.0000

Data Index: 22883 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.1552. Min Act: -0.0000

Data Index: 799906 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.2953. Min Act: -0.0001

Data Index: 800153 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.2511. Min Act: -0.0000

Data Index: 1050868 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.0265. Min Act: -0.0000

Data Index: 1096920 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.0085. Min Act: -0.0000

Data Index: 10298 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 7.4570. Min Range: -7.4570

Max Act: 6.1812. Min Act: -0.0000

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 7.4570. Min Range: -7.4570

Max Act: 5.5819. Min Act: -0.0000

Data Index: 1070845 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 7.4570. Min Range: -7.4570

Max Act: 5.7555. Min Act: -0.0000

Data Index: 946444 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 7.4570. Min Range: -7.4570

Max Act: 5.5620. Min Act: -0.0000

Data Index: 154462 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 7.4570. Min Range: -7.4570

Max Act: 5.6765. Min Act: -0.0000

Data Index: 1168827 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 7.4570. Min Range: -7.4570

Max Act: 5.6696. Min Act: -0.0001

Data Index: 318494 (C4 (Web Text))

Max Activating Token Index: 570