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

Dataset: The Pile

Neuron 4025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1586575 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3026. Min Act: -0.0000

Data Index: 239165 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3062. Min Act: -0.0000

Data Index: 759676 (The Pile)

Max Activating Token Index: 961

Text #3

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1441430 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1797846 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.1668. Min Act: -0.0000

Data Index: 730054 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1940093 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0781. Min Act: -0.0000

Data Index: 993483 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0964. Min Act: -0.0000

Data Index: 33671 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1604384 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1201306 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 1.4961. Min Range: -1.4961

Max Act: 0.9821. Min Act: -0.0000

Data Index: 792809 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0133. Min Act: -0.0000

Data Index: 271978 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1553165 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1511878 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.4961. Min Range: -1.4961

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1417311 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1577347 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0409. Min Act: 0.0000

Data Index: 1764612 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0030. Min Act: -0.0000

Data Index: 500868 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1897268 (The Pile)

Max Activating Token Index: 251