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

Dataset: The Pile

Neuron 2320 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: 1.1921. Min Range: -1.1921

Max Act: 1.1921. Min Act: -0.0000

Data Index: 837617 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 1.1921. Min Range: -1.1921

Max Act: 1.1221. Min Act: -0.0000

Data Index: 456083 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 1.1921. Min Range: -1.1921

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1155907 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.9305. Min Act: -0.0000

Data Index: 865177 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1487670 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1152631 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1908803 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.8134. Min Act: -0.0000

Data Index: 895123 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7585. Min Act: -0.0000

Data Index: 89251 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7378. Min Act: -0.0000

Data Index: 882061 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1116381 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7070. Min Act: -0.0000

Data Index: 837250 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1435076 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.7405. Min Act: -0.0000

Data Index: 589870 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6900. Min Act: 0.0000

Data Index: 75219 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1963855 (The Pile)

Max Activating Token Index: 718

Text #16

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.5982. Min Act: -0.0000

Data Index: 728231 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6225. Min Act: -0.0000

Data Index: 712711 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.5987. Min Act: -0.0000

Data Index: 737603 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 1.1921. Min Range: -1.1921

Max Act: 0.6149. Min Act: -0.0000

Data Index: 570512 (The Pile)

Max Activating Token Index: 692