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

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

Neuron 475 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0619. Min Range: -2.0619

Max Act: 2.0619. Min Act: 0.0000

Data Index: 696756 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.6764. Min Act: -0.0000

Data Index: 794652 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.6372. Min Act: 0.0001

Data Index: 249325 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.4868. Min Act: -0.0000

Data Index: 773429 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3286. Min Act: -0.0000

Data Index: 672886 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.4985. Min Act: 0.0000

Data Index: 1068962 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1101227 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3263. Min Act: 0.0002

Data Index: 1163366 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.2855. Min Act: 0.0000

Data Index: 709295 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.4561. Min Act: 0.0000

Data Index: 403248 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3448. Min Act: 0.0000

Data Index: 891167 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3852. Min Act: 0.0001

Data Index: 75865 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.2199. Min Act: -0.0000

Data Index: 879186 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3407. Min Act: 0.0001

Data Index: 496007 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.1154. Min Act: -0.0000

Data Index: 566215 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.3449. Min Act: 0.0000

Data Index: 1160525 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.1996. Min Act: -0.0000

Data Index: 158864 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.2594. Min Act: -0.0000

Data Index: 950140 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.2330. Min Act: 0.0001

Data Index: 736147 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 2.0619. Min Range: -2.0619

Max Act: 1.1616. Min Act: -0.0000

Data Index: 686996 (C4 (Web Text))

Max Activating Token Index: 783