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

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

Neuron 3140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6857. Min Act: -0.0000

Data Index: 758745 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6932. Min Act: -0.0000

Data Index: 75375 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6730. Min Act: -0.0000

Data Index: 515864 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6562. Min Act: -0.0000

Data Index: 509013 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6263. Min Act: -0.0000

Data Index: 534322 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6063. Min Act: -0.0000

Data Index: 711888 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6055. Min Act: -0.0000

Data Index: 237481 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5854. Min Act: -0.0000

Data Index: 618822 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.6043. Min Act: -0.0000

Data Index: 508907 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5849. Min Act: -0.0000

Data Index: 454763 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5674. Min Act: -0.0000

Data Index: 689960 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1084126 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5741. Min Act: -0.0000

Data Index: 161692 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5333. Min Act: -0.0000

Data Index: 174586 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1231655 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5497. Min Act: -0.0000

Data Index: 526245 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5244. Min Act: -0.0000

Data Index: 173364 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1002059 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5388. Min Act: -0.0000

Data Index: 841172 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.6932. Min Range: -0.6932

Max Act: 0.5537. Min Act: -0.0000

Data Index: 269206 (C4 (Web Text))

Max Activating Token Index: 95