Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4511. Min Act: -0.0000

Data Index: 924323 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1195851 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3270. Min Act: -0.0000

Data Index: 333239 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1230969 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1040177 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1201181 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3200. Min Act: -0.0000

Data Index: 359300 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2842. Min Act: -0.0000

Data Index: 628366 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3013. Min Act: -0.0000

Data Index: 475612 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2532. Min Act: -0.0000

Data Index: 668687 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2975. Min Act: -0.0000

Data Index: 610971 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2572. Min Act: -0.0000

Data Index: 482304 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2495. Min Act: -0.0000

Data Index: 860264 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2462. Min Act: -0.0000

Data Index: 401316 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2402. Min Act: -0.0000

Data Index: 333775 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2495. Min Act: -0.0000

Data Index: 312257 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2386. Min Act: -0.0000

Data Index: 379453 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1207025 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2367. Min Act: -0.0000

Data Index: 904464 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.2339. Min Act: -0.0000

Data Index: 379576 (C4 (Web Text))

Max Activating Token Index: 859