Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4818 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1432. Min Range: -2.1432

Max Act: 2.1432. Min Act: -0.0000

Data Index: 225080 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 2.1432. Min Range: -2.1432

Max Act: 2.0052. Min Act: -0.0000

Data Index: 1189296 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.4632. Min Act: -0.0000

Data Index: 458185 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.5992. Min Act: -0.0000

Data Index: 1196403 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.4708. Min Act: -0.0000

Data Index: 205006 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.3649. Min Act: -0.0000

Data Index: 78289 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1118644 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.2475. Min Act: -0.0000

Data Index: 406982 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.2108. Min Act: -0.0000

Data Index: 236623 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1220586 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.1327. Min Act: -0.0000

Data Index: 841515 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.1198. Min Act: -0.0000

Data Index: 896131 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1188613 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0766. Min Act: -0.0000

Data Index: 34355 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0484. Min Act: -0.0000

Data Index: 668350 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0406. Min Act: -0.0000

Data Index: 669764 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1143894 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0380. Min Act: -0.0000

Data Index: 257898 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1021493 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 2.1432. Min Range: -2.1432

Max Act: 1.0965. Min Act: -0.0000

Data Index: 900784 (C4 (Web Text))

Max Activating Token Index: 696