Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4308 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0569. Min Act: -0.0001

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0001

Data Index: 729952 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1096731 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1619050 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0444. Min Act: -0.0001

Data Index: 512344 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0471. Min Act: -0.0001

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1143060 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0451. Min Act: -0.0001

Data Index: 545867 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0446. Min Act: -0.0001

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0476. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0444. Min Act: -0.0001

Data Index: 954115 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0427. Min Act: -0.0001

Data Index: 428240 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0436. Min Act: -0.0001

Data Index: 317984 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1184540 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0447. Min Act: -0.0001

Data Index: 337626 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1256982 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0432. Min Act: -0.0001

Data Index: 21017 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1191605 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0425. Min Act: -0.0001

Data Index: 712515 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1313904 (C4 (Web Text))

Max Activating Token Index: 861