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

Dataset: The Pile

Neuron 4504 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: 0.5002. Min Range: -0.5002

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1256357 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1783736 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1175999 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1972317 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4775. Min Act: -0.0000

Data Index: 221644 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4552. Min Act: -0.0000

Data Index: 229986 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1953311 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1591546 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4170. Min Act: -0.0000

Data Index: 764424 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1933285 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1149073 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4251. Min Act: -0.0000

Data Index: 718921 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1288128 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1911464 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4604. Min Act: -0.0000

Data Index: 96836 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1306017 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1542700 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1337593 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3631. Min Act: -0.0000

Data Index: 125279 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3901. Min Act: -0.0000

Data Index: 198178 (The Pile)

Max Activating Token Index: 50