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

Dataset: The Pile

Neuron 1646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1395081 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 1.3116. Min Range: -1.3116

Max Act: 1.0870. Min Act: -0.0000

Data Index: 556965 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.9442. Min Act: -0.0000

Data Index: 242505 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1767233 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8831. Min Act: -0.0000

Data Index: 992579 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.9915. Min Act: -0.0000

Data Index: 393001 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1325965 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1462291 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.9140. Min Act: -0.0000

Data Index: 858978 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.9212. Min Act: -0.0000

Data Index: 857735 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1772998 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8223. Min Act: -0.0000

Data Index: 926614 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1677774 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8927. Min Act: -0.0000

Data Index: 793998 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8996. Min Act: -0.0000

Data Index: 288321 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8930. Min Act: -0.0000

Data Index: 380255 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1977959 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.8114. Min Act: -0.0000

Data Index: 147599 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1860462 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 1.3116. Min Range: -1.3116

Max Act: 0.7908. Min Act: -0.0000

Data Index: 725803 (The Pile)

Max Activating Token Index: 874