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

Dataset: The Pile

Neuron 476 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: 1.3429. Min Range: -1.3429

Max Act: 1.3429. Min Act: -0.0000

Data Index: 887425 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1822. Min Act: -0.0000

Data Index: 822852 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1389702 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1158. Min Act: -0.0000

Data Index: 331107 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0748. Min Act: -0.0000

Data Index: 436649 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.2094. Min Act: -0.0000

Data Index: 922993 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0794. Min Act: -0.0000

Data Index: 745520 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0442. Min Act: -0.0000

Data Index: 604303 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1021666 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1445833 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1061498 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1257091 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1048407 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1850969 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1579248 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1431183 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0639. Min Act: -0.0000

Data Index: 706887 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1186282 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 1.3429. Min Range: -1.3429

Max Act: 1.0101. Min Act: -0.0000

Data Index: 551953 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 1.3429. Min Range: -1.3429

Max Act: 0.9441. Min Act: -0.0000

Data Index: 741182 (The Pile)

Max Activating Token Index: 715