Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4905 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0505. Min Range: -1.0505

Max Act: 1.0505. Min Act: -0.0000

Data Index: 365683 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1036296 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.8131. Min Act: 0.0000

Data Index: 610322 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.7353. Min Act: 0.0000

Data Index: 807855 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.7349. Min Act: -0.0000

Data Index: 210462 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6936. Min Act: -0.0000

Data Index: 112965 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6448. Min Act: -0.0000

Data Index: 93926 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1209460 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6495. Min Act: -0.0000

Data Index: 891226 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6807. Min Act: -0.0000

Data Index: 384239 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1060355 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6105. Min Act: -0.0000

Data Index: 915046 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1140419 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1277747 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.5929. Min Act: 0.0000

Data Index: 140767 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.5259. Min Act: -0.0000

Data Index: 617552 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.6008. Min Act: -0.0000

Data Index: 576292 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.5171. Min Act: -0.0000

Data Index: 580955 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.5240. Min Act: -0.0000

Data Index: 92680 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 1.0505. Min Range: -1.0505

Max Act: 0.5062. Min Act: -0.0000

Data Index: 427986 (C4 (Web Text))

Max Activating Token Index: 737