Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2992. Min Act: -0.0001

Data Index: 769961 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3356. Min Act: -0.0001

Data Index: 24474 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3219. Min Act: -0.0001

Data Index: 272518 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2849. Min Act: -0.0001

Data Index: 581563 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2754. Min Act: -0.0001

Data Index: 109240 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2876. Min Act: -0.0001

Data Index: 709812 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1081726 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2559. Min Act: -0.0001

Data Index: 763897 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2544. Min Act: -0.0001

Data Index: 470471 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1324972 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2607. Min Act: -0.0001

Data Index: 776797 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1073583 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2560. Min Act: -0.0001

Data Index: 543850 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2420. Min Act: -0.0001

Data Index: 249807 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2349. Min Act: -0.0001

Data Index: 1295922 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1116614 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1239397 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2376. Min Act: -0.0000

Data Index: 49624 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2377. Min Act: -0.0001

Data Index: 431366 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2384. Min Act: -0.0001

Data Index: 805680 (C4 (Web Text))

Max Activating Token Index: 446