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

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

Neuron 4691 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.5471. Min Act: -0.0001

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1013. Min Act: -0.0001

Data Index: 1067645 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 4.5471. Min Range: -4.5471

Max Act: 3.8298. Min Act: -0.0001

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 4.5471. Min Range: -4.5471

Max Act: 3.9511. Min Act: -0.0001

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 4.5471. Min Range: -4.5471

Max Act: 3.5173. Min Act: -0.0001

Data Index: 658215 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 4.5471. Min Range: -4.5471

Max Act: 3.1074. Min Act: -0.0000

Data Index: 615999 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.9415. Min Act: -0.0001

Data Index: 1053495 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.9525. Min Act: -0.0001

Data Index: 307827 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.8906. Min Act: -0.0001

Data Index: 515498 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.7803. Min Act: -0.0001

Data Index: 226727 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 4.5471. Min Range: -4.5471

Max Act: 3.1147. Min Act: -0.0001

Data Index: 598784 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.6302. Min Act: -0.0001

Data Index: 468433 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.9029. Min Act: -0.0000

Data Index: 311216 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.9465. Min Act: -0.0001

Data Index: 1150957 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.7687. Min Act: -0.0001

Data Index: 811213 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.5184. Min Act: -0.0001

Data Index: 1224566 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.7963. Min Act: -0.0000

Data Index: 646948 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.8808. Min Act: -0.0001

Data Index: 939875 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.7063. Min Act: -0.0000

Data Index: 858417 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 4.5471. Min Range: -4.5471

Max Act: 2.7381. Min Act: -0.0001

Data Index: 472354 (C4 (Web Text))

Max Activating Token Index: 902