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

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

Neuron 3551 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: 3.0858. Min Range: -3.0858

Max Act: 3.0858. Min Act: -0.0000

Data Index: 365409 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.8104. Min Act: -0.0000

Data Index: 271559 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.5182. Min Act: -0.0000

Data Index: 465172 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.7512. Min Act: -0.0000

Data Index: 221966 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.3739. Min Act: -0.0000

Data Index: 681404 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.4403. Min Act: -0.0000

Data Index: 102478 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.1609. Min Act: -0.0000

Data Index: 128557 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.1622. Min Act: -0.0000

Data Index: 932130 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.3867. Min Act: -0.0000

Data Index: 636408 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.4907. Min Act: -0.0001

Data Index: 20075 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.2353. Min Act: -0.0000

Data Index: 177278 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.3469. Min Act: -0.0001

Data Index: 1329120 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.3408. Min Act: -0.0000

Data Index: 557670 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.1827. Min Act: -0.0000

Data Index: 579949 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.0369. Min Act: -0.0000

Data Index: 1128167 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.1426. Min Act: -0.0000

Data Index: 1167000 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.1218. Min Act: -0.0001

Data Index: 556068 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.2328. Min Act: -0.0000

Data Index: 195745 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.3186. Min Act: -0.0000

Data Index: 634668 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.0858. Min Range: -3.0858

Max Act: 2.0804. Min Act: -0.0000

Data Index: 342227 (C4 (Web Text))

Max Activating Token Index: 855