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

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

Neuron 2015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.1536. Min Act: -0.0000

Data Index: 853067 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0626. Min Act: -0.0000

Data Index: 869275 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0669. Min Act: -0.0000

Data Index: 608059 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0958. Min Act: -0.0000

Data Index: 672748 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0433. Min Act: -0.0000

Data Index: 805937 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0325. Min Act: -0.0000

Data Index: 644268 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1276451 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.1536. Min Range: -1.1536

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1282079 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9928. Min Act: -0.0000

Data Index: 957227 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1184347 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9749. Min Act: -0.0000

Data Index: 887185 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1329357 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1179543 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9551. Min Act: -0.0000

Data Index: 427184 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9751. Min Act: -0.0000

Data Index: 134662 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9763. Min Act: -0.0000

Data Index: 444664 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9055. Min Act: -0.0000

Data Index: 76781 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9399. Min Act: -0.0000

Data Index: 713831 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9647. Min Act: -0.0000

Data Index: 654808 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1354791 (C4 (Web Text))

Max Activating Token Index: 23