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

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

Neuron 1614 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1331611 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0500. Min Act: -0.0001

Data Index: 737293 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0482. Min Act: -0.0001

Data Index: 224533 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0476. Min Act: -0.0001

Data Index: 331044 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0478. Min Act: -0.0001

Data Index: 351908 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0460. Min Act: -0.0001

Data Index: 124945 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1025362 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0428. Min Act: -0.0001

Data Index: 803377 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0424. Min Act: -0.0001

Data Index: 257477 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0397. Min Act: -0.0001

Data Index: 96616 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0406. Min Act: -0.0001

Data Index: 555466 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0400. Min Act: -0.0001

Data Index: 391994 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0395. Min Act: -0.0001

Data Index: 931093 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0385. Min Act: -0.0001

Data Index: 725816 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1093747 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0385. Min Act: -0.0001

Data Index: 378697 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0381. Min Act: -0.0001

Data Index: 64322 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0396. Min Act: -0.0001

Data Index: 610745 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0388. Min Act: -0.0001

Data Index: 927628 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.0500. Min Range: -0.0500

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1974 (C4 (Web Text))

Max Activating Token Index: 585