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

Dataset: The Pile

Neuron 2715 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.8337. Min Act: -0.0000

Data Index: 241082 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.8397. Min Act: -0.0000

Data Index: 506009 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6974. Min Act: -0.0000

Data Index: 505872 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6781. Min Act: -0.0000

Data Index: 11470 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.7533. Min Act: -0.0000

Data Index: 676884 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1900183 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1493795 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1742177 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1551365 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6247. Min Act: -0.0000

Data Index: 781735 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6019. Min Act: -0.0000

Data Index: 972452 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6372. Min Act: -0.0000

Data Index: 35735 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5989. Min Act: -0.0000

Data Index: 831491 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6140. Min Act: -0.0000

Data Index: 290871 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5993. Min Act: -0.0000

Data Index: 72822 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5990. Min Act: -0.0000

Data Index: 211946 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5881. Min Act: -0.0000

Data Index: 688511 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5877. Min Act: -0.0000

Data Index: 269828 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1744131 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5742. Min Act: -0.0000

Data Index: 480526 (The Pile)

Max Activating Token Index: 811