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

Dataset: The Pile

Neuron 3883 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: 0.3598. Min Range: -0.3598

Max Act: 0.3598. Min Act: -0.0000

Data Index: 144373 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1429055 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1105348 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1501192 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3289. Min Act: -0.0000

Data Index: 251582 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1224627 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1163353 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3332. Min Act: -0.0000

Data Index: 948407 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1404004 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3130. Min Act: -0.0000

Data Index: 850055 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1365547 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1496708 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1702286 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2877. Min Act: -0.0000

Data Index: 967086 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2906. Min Act: -0.0000

Data Index: 786942 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2875. Min Act: -0.0000

Data Index: 222371 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1458026 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1218393 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2799. Min Act: -0.0000

Data Index: 188524 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1794208 (The Pile)

Max Activating Token Index: 661