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

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

Neuron 1520 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8507. Min Act: -0.0001

Data Index: 1412738 (Python Code)

Max Activating Token Index: 689

Text #1

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8906. Min Act: -0.0001

Data Index: 848423 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8101. Min Act: -0.0001

Data Index: 392316 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8367. Min Act: -0.0001

Data Index: 52318 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7919. Min Act: -0.0001

Data Index: 1321724 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8176. Min Act: -0.0001

Data Index: 1102224 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7778. Min Act: -0.0001

Data Index: 939403 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7940. Min Act: -0.0001

Data Index: 250881 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7629. Min Act: -0.0001

Data Index: 811915 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7814. Min Act: -0.0001

Data Index: 887329 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7457. Min Act: -0.0001

Data Index: 460905 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1268040 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1332454 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7370. Min Act: -0.0001

Data Index: 74974 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7592. Min Act: -0.0001

Data Index: 828648 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7796. Min Act: -0.0001

Data Index: 154492 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7708. Min Act: -0.0001

Data Index: 833838 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1038497 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7482. Min Act: -0.0001

Data Index: 422794 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7686. Min Act: -0.0001

Data Index: 597268 (C4 (Web Text))

Max Activating Token Index: 675