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

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

Neuron 1803 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2391. Min Range: -2.2391

Max Act: 2.2391. Min Act: -0.0001

Data Index: 651085 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1191446 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.4753. Min Act: -0.0000

Data Index: 616709 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.6304. Min Act: -0.0000

Data Index: 1258668 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.4302. Min Act: -0.0000

Data Index: 777210 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.5032. Min Act: -0.0000

Data Index: 208414 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.3706. Min Act: -0.0000

Data Index: 618498 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.4306. Min Act: -0.0000

Data Index: 544628 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2855. Min Act: -0.0000

Data Index: 331918 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.3754. Min Act: -0.0000

Data Index: 202032 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1277874 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.3305. Min Act: -0.0000

Data Index: 706226 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1332671 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.1606. Min Act: -0.0000

Data Index: 922751 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1001020 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2879. Min Act: -0.0000

Data Index: 975606 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2874. Min Act: -0.0000

Data Index: 882680 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2649. Min Act: -0.0000

Data Index: 345344 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.1624. Min Act: -0.0000

Data Index: 592809 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 2.2391. Min Range: -2.2391

Max Act: 1.2340. Min Act: -0.0000

Data Index: 707830 (C4 (Web Text))

Max Activating Token Index: 176