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

Dataset: The Pile

Neuron 2277 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: 1.8070. Min Range: -1.8070

Max Act: 1.8070. Min Act: -0.0000

Data Index: 134959 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1061320 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.7829. Min Act: -0.0000

Data Index: 1887986 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5180. Min Act: -0.0000

Data Index: 1769147 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.7077. Min Act: -0.0000

Data Index: 1261483 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.7780. Min Act: -0.0000

Data Index: 188919 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5784. Min Act: -0.0000

Data Index: 56489 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5910. Min Act: -0.0000

Data Index: 358893 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1568072 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1457344 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.7627. Min Act: -0.0000

Data Index: 1692490 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4557. Min Act: -0.0000

Data Index: 729594 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1492370 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4257. Min Act: -0.0000

Data Index: 1428676 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1143828 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1603791 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1454329 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1666622 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1452180 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.3994. Min Act: -0.0000

Data Index: 1599833 (The Pile)

Max Activating Token Index: 942