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

Dataset: The Pile

Neuron 4317 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4434. Min Range: -3.4434

Max Act: 3.4434. Min Act: -0.0000

Data Index: 479111 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 3.4434. Min Range: -3.4434

Max Act: 3.2592. Min Act: -0.0000

Data Index: 900172 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.9741. Min Act: -0.0000

Data Index: 1744883 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 3.4434. Min Range: -3.4434

Max Act: 3.0961. Min Act: -0.0000

Data Index: 1034630 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.8175. Min Act: -0.0000

Data Index: 1255319 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.7170. Min Act: -0.0000

Data Index: 960741 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.5799. Min Act: -0.0000

Data Index: 63784 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.6905. Min Act: -0.0000

Data Index: 1515766 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.6174. Min Act: -0.0000

Data Index: 1449483 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.5924. Min Act: -0.0000

Data Index: 1399180 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.4684. Min Act: -0.0000

Data Index: 979473 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.7094. Min Act: -0.0000

Data Index: 558715 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.4195. Min Act: -0.0000

Data Index: 1811232 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.4841. Min Act: -0.0000

Data Index: 510572 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.7104. Min Act: -0.0000

Data Index: 1847606 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.3249. Min Act: -0.0000

Data Index: 103425 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.5884. Min Act: -0.0000

Data Index: 1996804 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.5691. Min Act: -0.0000

Data Index: 700250 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.4455. Min Act: -0.0000

Data Index: 156783 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 3.4434. Min Range: -3.4434

Max Act: 2.5387. Min Act: -0.0000

Data Index: 814649 (The Pile)

Max Activating Token Index: 473