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

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

Neuron 890 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4498. Min Range: -3.4498

Max Act: 3.4498. Min Act: -0.0000

Data Index: 1316541 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.4498. Min Range: -3.4498

Max Act: 3.1699. Min Act: -0.0000

Data Index: 224356 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.8665. Min Act: -0.0000

Data Index: 561264 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.8236. Min Act: -0.0000

Data Index: 587596 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.8649. Min Act: -0.0000

Data Index: 616015 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.7535. Min Act: -0.0000

Data Index: 102401 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.8667. Min Act: -0.0000

Data Index: 1193113 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.8168. Min Act: -0.0000

Data Index: 114317 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.6003. Min Act: -0.0000

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.2413. Min Act: -0.0000

Data Index: 829984 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.2684. Min Act: -0.0000

Data Index: 161331 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.0738. Min Act: -0.0000

Data Index: 889277 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.0561. Min Act: -0.0000

Data Index: 838287 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.4498. Min Range: -3.4498

Max Act: 1.9657. Min Act: -0.0000

Data Index: 654243 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.0430. Min Act: -0.0000

Data Index: 1031508 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 3.4498. Min Range: -3.4498

Max Act: 1.6461. Min Act: -0.0000

Data Index: 284121 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 3.4498. Min Range: -3.4498

Max Act: 1.7944. Min Act: -0.0000

Data Index: 1314658 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 3.4498. Min Range: -3.4498

Max Act: 1.7118. Min Act: -0.0000

Data Index: 592390 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 3.4498. Min Range: -3.4498

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1051794 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 3.4498. Min Range: -3.4498

Max Act: 2.0187. Min Act: -0.0000

Data Index: 951175 (C4 (Web Text))

Max Activating Token Index: 238