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

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

Neuron 3625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0001

Data Index: 601964 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0554. Min Act: -0.0001

Data Index: 757546 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0535. Min Act: -0.0001

Data Index: 981747 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0509. Min Act: -0.0001

Data Index: 633148 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0519. Min Act: -0.0001

Data Index: 804627 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0456. Min Act: -0.0001

Data Index: 579565 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0464. Min Act: -0.0000

Data Index: 671924 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0435. Min Act: -0.0001

Data Index: 27464 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0445. Min Act: -0.0001

Data Index: 970500 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0411. Min Act: -0.0001

Data Index: 870982 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0453. Min Act: -0.0001

Data Index: 127649 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1169086 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0407. Min Act: -0.0001

Data Index: 819590 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1272578 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0400. Min Act: -0.0001

Data Index: 420641 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0414. Min Act: -0.0001

Data Index: 636798 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1273890 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0411. Min Act: -0.0001

Data Index: 43755 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0425. Min Act: -0.0001

Data Index: 894305 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1258272 (C4 (Web Text))

Max Activating Token Index: 126