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

Dataset: The Pile

Neuron 2913 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: 1.2225. Min Range: -1.2225

Max Act: 1.2225. Min Act: 0.0000

Data Index: 1746088 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1465083 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1807296 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9719. Min Act: -0.0000

Data Index: 306102 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0150. Min Act: -0.0000

Data Index: 604600 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0047. Min Act: -0.0000

Data Index: 942401 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9823. Min Act: -0.0000

Data Index: 988886 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0207. Min Act: -0.0000

Data Index: 728121 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.2225. Min Range: -1.2225

Max Act: 1.0061. Min Act: -0.0000

Data Index: 215600 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1966251 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8777. Min Act: -0.0000

Data Index: 859921 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9308. Min Act: -0.0000

Data Index: 804087 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1107885 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8723. Min Act: -0.0000

Data Index: 660036 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8733. Min Act: -0.0000

Data Index: 854498 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1860412 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.9156. Min Act: -0.0000

Data Index: 30659 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8023. Min Act: -0.0000

Data Index: 102026 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1733861 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 1.2225. Min Range: -1.2225

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1756032 (The Pile)

Max Activating Token Index: 291