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

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

Neuron 1702 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1291. Min Act: -0.0001

Data Index: 154367 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1038. Min Act: -0.0000

Data Index: 762862 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0873. Min Act: 0.0001

Data Index: 653795 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1317628 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0840. Min Act: 0.0001

Data Index: 104774 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0839. Min Act: -0.0001

Data Index: 163293 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1010643 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1086411 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1242520 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0791. Min Act: -0.0000

Data Index: 209596 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0783. Min Act: 0.0000

Data Index: 62284 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0821. Min Act: -0.0000

Data Index: 535173 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0813. Min Act: -0.0000

Data Index: 181961 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0798. Min Act: -0.0000

Data Index: 11188 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0780. Min Act: -0.0001

Data Index: 657035 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0769. Min Act: 0.0000

Data Index: 390174 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0772. Min Act: -0.0000

Data Index: 694466 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0766. Min Act: -0.0000

Data Index: 420694 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0761. Min Act: -0.0000

Data Index: 37611 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1225 (C4 (Web Text))

Max Activating Token Index: 945