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

Dataset: The Pile

Neuron 1766 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1008490 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4663. Min Act: 0.0000

Data Index: 1894583 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1649769 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4883. Min Act: 0.0000

Data Index: 1949167 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4825. Min Act: -0.0000

Data Index: 830183 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1519515 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2891. Min Act: -0.0000

Data Index: 324891 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1146819 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1481294 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1621032 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4131. Min Act: -0.0000

Data Index: 738570 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1470967 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2469. Min Act: -0.0000

Data Index: 1191854 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1536201 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3268. Min Act: -0.0000

Data Index: 882025 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3034. Min Act: 0.0000

Data Index: 1429482 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2897. Min Act: 0.0000

Data Index: 1749616 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1029293 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1139860 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1742319 (The Pile)

Max Activating Token Index: 888