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

Dataset: The Pile

Neuron 244 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4913. Min Act: -0.0000

Data Index: 760526 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3938. Min Act: -0.0000

Data Index: 333941 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3344. Min Act: -0.0000

Data Index: 229531 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3163. Min Act: -0.0000

Data Index: 980629 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1311627 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1875373 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3070. Min Act: 0.0000

Data Index: 383446 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1738980 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3086. Min Act: -0.0000

Data Index: 919852 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1558608 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2644. Min Act: -0.0000

Data Index: 337013 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2799. Min Act: -0.0000

Data Index: 546556 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1321291 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2563. Min Act: -0.0000

Data Index: 156300 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1692866 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1480096 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1629263 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1692489 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2569. Min Act: -0.0000

Data Index: 340217 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.2665. Min Act: -0.0000

Data Index: 547916 (The Pile)

Max Activating Token Index: 373