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

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

Neuron 225 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1180171 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1089658 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4972. Min Act: -0.0001

Data Index: 914181 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.6029. Min Act: -0.0001

Data Index: 631625 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5442. Min Act: -0.0001

Data Index: 1244917 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4946. Min Act: -0.0001

Data Index: 785305 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4543. Min Act: -0.0001

Data Index: 468623 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4975. Min Act: -0.0001

Data Index: 443019 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4228. Min Act: -0.0001

Data Index: 815067 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4523. Min Act: -0.0001

Data Index: 543930 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4670. Min Act: -0.0001

Data Index: 264848 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4571. Min Act: -0.0001

Data Index: 511443 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4474. Min Act: -0.0001

Data Index: 1175564 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4299. Min Act: -0.0001

Data Index: 351263 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4061. Min Act: -0.0001

Data Index: 950318 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4154. Min Act: -0.0000

Data Index: 635963 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4015. Min Act: -0.0001

Data Index: 930847 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1057572 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.3945. Min Act: -0.0001

Data Index: 626877 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4035. Min Act: -0.0001

Data Index: 462876 (C4 (Web Text))

Max Activating Token Index: 613