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

Dataset: The Pile

Neuron 3627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4747. Min Act: -0.0000

Data Index: 216607 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1535520 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1000238 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1274662 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3699. Min Act: -0.0000

Data Index: 152257 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3308. Min Act: -0.0000

Data Index: 329328 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3524. Min Act: -0.0000

Data Index: 776128 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1614422 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2898. Min Act: -0.0000

Data Index: 175171 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1859881 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3134. Min Act: -0.0000

Data Index: 367732 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1340694 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2863. Min Act: -0.0000

Data Index: 7225 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3321. Min Act: -0.0000

Data Index: 236898 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1485158 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2805. Min Act: -0.0000

Data Index: 43300 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2623. Min Act: -0.0000

Data Index: 220416 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2978. Min Act: -0.0000

Data Index: 283929 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2996. Min Act: -0.0000

Data Index: 241990 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.4747. Min Range: -0.4747

Max Act: 0.2779. Min Act: -0.0000

Data Index: 569934 (The Pile)

Max Activating Token Index: 939