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

Dataset: The Pile

Neuron 3732 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: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0000

Data Index: 998318 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1731282 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1521257 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1110365 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1447336 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1934477 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1996044 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1134382 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1650622 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2765. Min Act: -0.0000

Data Index: 505827 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2915. Min Act: -0.0000

Data Index: 257492 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1041957 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1293687 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2739. Min Act: -0.0000

Data Index: 817386 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1875913 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2325. Min Act: -0.0000

Data Index: 133011 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1761399 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2422. Min Act: -0.0000

Data Index: 247804 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1644774 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.2290. Min Act: -0.0000

Data Index: 503118 (The Pile)

Max Activating Token Index: 843