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

Dataset: The Pile

Neuron 1787 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3350. Min Act: -0.0000

Data Index: 775943 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1871461 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1593287 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2819. Min Act: -0.0000

Data Index: 653430 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2427. Min Act: -0.0000

Data Index: 435475 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2574. Min Act: -0.0000

Data Index: 531203 (The Pile)

Max Activating Token Index: 881

Text #6

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2488. Min Act: -0.0000

Data Index: 541924 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2553. Min Act: -0.0000

Data Index: 24552 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2447. Min Act: -0.0000

Data Index: 898917 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2541. Min Act: -0.0000

Data Index: 307130 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2446. Min Act: -0.0000

Data Index: 98926 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1577324 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1860894 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2281. Min Act: -0.0000

Data Index: 618221 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1159989 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2467. Min Act: -0.0000

Data Index: 388811 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2432. Min Act: -0.0000

Data Index: 899135 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1795197 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1190351 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1275484 (The Pile)

Max Activating Token Index: 705