Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 174 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3316. Min Act: -0.0001

Data Index: 6919 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3188. Min Act: -0.0001

Data Index: 997172 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2923. Min Act: -0.0001

Data Index: 7278 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2904. Min Act: -0.0001

Data Index: 822691 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2639. Min Act: -0.0001

Data Index: 682962 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2657. Min Act: -0.0001

Data Index: 510170 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2793. Min Act: -0.0000

Data Index: 962489 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1304829 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2737. Min Act: -0.0001

Data Index: 1005779 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2693. Min Act: -0.0001

Data Index: 1195172 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2428. Min Act: -0.0001

Data Index: 765510 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2640. Min Act: -0.0001

Data Index: 488041 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1114549 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2532. Min Act: -0.0001

Data Index: 122470 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1045675 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2492. Min Act: -0.0001

Data Index: 959088 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1118650 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2500. Min Act: -0.0001

Data Index: 458174 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2391. Min Act: -0.0001

Data Index: 636352 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2461. Min Act: -0.0001

Data Index: 713652 (C4 (Web Text))

Max Activating Token Index: 1013