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

Dataset: The Pile

Neuron 4786 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.7061. Min Act: -0.0000

Data Index: 459783 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.5886. Min Act: -0.0000

Data Index: 465308 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.7287. Min Act: -0.0000

Data Index: 368647 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.0452. Min Act: -0.0000

Data Index: 1594054 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.3821. Min Act: -0.0000

Data Index: 1114606 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.0710. Min Act: -0.0000

Data Index: 1422834 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.1942. Min Act: -0.0000

Data Index: 228711 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.9522. Min Act: -0.0000

Data Index: 1921027 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.8746. Min Act: -0.0000

Data Index: 1276722 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.0290. Min Act: -0.0000

Data Index: 67378 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.9869. Min Act: -0.0000

Data Index: 1257126 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.1437. Min Act: -0.0000

Data Index: 1651938 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.6237. Min Act: -0.0000

Data Index: 1804940 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.9043. Min Act: -0.0000

Data Index: 471355 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 4.7287. Min Range: -4.7287

Max Act: 4.0746. Min Act: -0.0000

Data Index: 1890354 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.8907. Min Act: -0.0000

Data Index: 220312 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.8760. Min Act: -0.0000

Data Index: 1480340 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.8317. Min Act: -0.0000

Data Index: 874592 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.7122. Min Act: -0.0000

Data Index: 1683274 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 4.7287. Min Range: -4.7287

Max Act: 3.8115. Min Act: -0.0000

Data Index: 1156407 (The Pile)

Max Activating Token Index: 114