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

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

Neuron 510 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: 0.3633. Min Range: -0.3633

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1225905 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3069. Min Act: -0.0000

Data Index: 970752 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1239805 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1237725 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1196548 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2915. Min Act: -0.0000

Data Index: 674808 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2574. Min Act: -0.0000

Data Index: 555440 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2575. Min Act: -0.0000

Data Index: 722806 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2542. Min Act: -0.0000

Data Index: 176128 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2384. Min Act: -0.0000

Data Index: 66904 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2471. Min Act: -0.0000

Data Index: 891612 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1167187 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2238. Min Act: -0.0000

Data Index: 570679 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2322. Min Act: -0.0000

Data Index: 404219 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2377. Min Act: -0.0000

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1054140 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1204406 (C4 (Web Text))

Max Activating Token Index: 186