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

Dataset: The Pile

Neuron 1643 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: 1.4611. Min Range: -1.4611

Max Act: 1.4611. Min Act: -0.0000

Data Index: 45817 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.1642. Min Act: -0.0000

Data Index: 815177 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.4611. Min Range: -1.4611

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1652157 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9955. Min Act: -0.0000

Data Index: 957812 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1283433 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7846. Min Act: -0.0000

Data Index: 500883 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1683099 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7202. Min Act: -0.0000

Data Index: 193483 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1327562 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1535266 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1069286 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.8308. Min Act: -0.0000

Data Index: 392621 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1128120 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7965. Min Act: -0.0000

Data Index: 217276 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7421. Min Act: -0.0000

Data Index: 435086 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1096528 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.6923. Min Act: -0.0000

Data Index: 749023 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1222270 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1276139 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 1.4611. Min Range: -1.4611

Max Act: 0.6986. Min Act: -0.0000

Data Index: 214863 (The Pile)

Max Activating Token Index: 472