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

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

Neuron 175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2591. Min Range: -1.2591

Max Act: 1.2591. Min Act: -0.0001

Data Index: 477521 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.2591. Min Range: -1.2591

Max Act: 1.0061. Min Act: -0.0001

Data Index: 448754 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.2591. Min Range: -1.2591

Max Act: 1.0317. Min Act: -0.0001

Data Index: 777221 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.9106. Min Act: -0.0001

Data Index: 478983 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.9581. Min Act: -0.0001

Data Index: 324681 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8901. Min Act: -0.0001

Data Index: 854488 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8423. Min Act: -0.0001

Data Index: 149185 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8581. Min Act: -0.0001

Data Index: 203008 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8749. Min Act: -0.0001

Data Index: 376633 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8457. Min Act: -0.0001

Data Index: 1192832 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1099093 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8628. Min Act: -0.0001

Data Index: 230101 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8336. Min Act: -0.0001

Data Index: 79767 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8167. Min Act: -0.0001

Data Index: 857723 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8878. Min Act: -0.0001

Data Index: 700456 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8312. Min Act: -0.0001

Data Index: 1013670 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8063. Min Act: -0.0001

Data Index: 393296 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8766. Min Act: -0.0001

Data Index: 364649 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1185279 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 1.2591. Min Range: -1.2591

Max Act: 0.7827. Min Act: -0.0001

Data Index: 520232 (C4 (Web Text))

Max Activating Token Index: 105