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

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

Neuron 1585 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: 0.5929. Min Range: -0.5929

Max Act: 0.5901. Min Act: -0.0001

Data Index: 586394 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5649. Min Act: -0.0001

Data Index: 195136 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5929. Min Act: -0.0001

Data Index: 561210 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5397. Min Act: -0.0001

Data Index: 725425 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5475. Min Act: -0.0001

Data Index: 155636 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5011. Min Act: -0.0001

Data Index: 701779 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5134. Min Act: -0.0001

Data Index: 672030 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5110. Min Act: -0.0001

Data Index: 526184 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5273. Min Act: -0.0001

Data Index: 561868 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5071. Min Act: -0.0001

Data Index: 738132 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5322. Min Act: -0.0001

Data Index: 354809 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4803. Min Act: -0.0001

Data Index: 1085357 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5062. Min Act: -0.0001

Data Index: 391549 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5037. Min Act: -0.0001

Data Index: 299452 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4964. Min Act: -0.0001

Data Index: 750204 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4734. Min Act: -0.0001

Data Index: 509837 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4708. Min Act: -0.0001

Data Index: 1194548 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4703. Min Act: -0.0001

Data Index: 1171470 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4606. Min Act: -0.0001

Data Index: 525106 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4571. Min Act: -0.0001

Data Index: 1315128 (C4 (Web Text))

Max Activating Token Index: 270