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

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

Neuron 4782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1863. Min Range: -2.1863

Max Act: 2.1863. Min Act: -0.0000

Data Index: 81048 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.9800. Min Act: -0.0000

Data Index: 483535 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.9716. Min Act: -0.0000

Data Index: 744327 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.9493. Min Act: -0.0000

Data Index: 1271351 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.9448. Min Act: -0.0000

Data Index: 576744 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1268855 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8513. Min Act: -0.0000

Data Index: 119304 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7999. Min Act: -0.0000

Data Index: 505120 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8912. Min Act: -0.0000

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7780. Min Act: -0.0000

Data Index: 297401 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8346. Min Act: -0.0000

Data Index: 384846 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7611. Min Act: -0.0000

Data Index: 938248 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8634. Min Act: -0.0000

Data Index: 392138 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8120. Min Act: -0.0000

Data Index: 101545 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7858. Min Act: -0.0000

Data Index: 395716 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7865. Min Act: -0.0000

Data Index: 972319 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7254. Min Act: -0.0000

Data Index: 596992 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8621. Min Act: -0.0000

Data Index: 759325 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1327288 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1104408 (C4 (Web Text))

Max Activating Token Index: 273