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

Dataset: The Pile

Neuron 3981 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1348101 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4300. Min Act: -0.0000

Data Index: 191555 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3772. Min Act: -0.0000

Data Index: 380890 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4024. Min Act: -0.0000

Data Index: 651009 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4014. Min Act: -0.0000

Data Index: 437741 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3752. Min Act: -0.0000

Data Index: 66982 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1229562 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3695. Min Act: -0.0000

Data Index: 242268 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3637. Min Act: -0.0000

Data Index: 620964 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1033672 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1881898 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1033289 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1114980 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3382. Min Act: -0.0000

Data Index: 277760 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3578. Min Act: -0.0000

Data Index: 379148 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3584. Min Act: -0.0000

Data Index: 49343 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3388. Min Act: -0.0000

Data Index: 18 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3310. Min Act: -0.0000

Data Index: 973952 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3444. Min Act: -0.0000

Data Index: 300236 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1127247 (The Pile)

Max Activating Token Index: 945