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

Dataset: The Pile

Neuron 649 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1491922 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1991628 (The Pile)

Max Activating Token Index: 64

Text #2

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2936. Min Act: -0.0000

Data Index: 856657 (The Pile)

Max Activating Token Index: 838

Text #3

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1375763 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2396. Min Act: -0.0000

Data Index: 58569 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2490. Min Act: -0.0000

Data Index: 993743 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2172. Min Act: -0.0000

Data Index: 801726 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1805865 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2207. Min Act: -0.0000

Data Index: 245439 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2098. Min Act: -0.0000

Data Index: 662598 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1611729 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1578731 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1987. Min Act: -0.0000

Data Index: 346185 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2107. Min Act: -0.0000

Data Index: 169741 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2032. Min Act: -0.0000

Data Index: 581085 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1909000 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1531241 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1133839 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1139435 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2027. Min Act: -0.0000

Data Index: 302742 (The Pile)

Max Activating Token Index: 201