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

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

Neuron 904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2123. Min Range: -4.2123

Max Act: 4.2123. Min Act: -0.0000

Data Index: 812746 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.8333. Min Act: -0.0000

Data Index: 1153149 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.7033. Min Act: -0.0000

Data Index: 1086387 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.4865. Min Act: -0.0000

Data Index: 1154561 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.4871. Min Act: -0.0000

Data Index: 105393 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1973. Min Act: -0.0000

Data Index: 502637 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1748. Min Act: -0.0000

Data Index: 978275 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.3012. Min Act: -0.0000

Data Index: 1340237 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.3033. Min Act: -0.0000

Data Index: 11783 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.2812. Min Act: -0.0000

Data Index: 1339122 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1615. Min Act: -0.0000

Data Index: 1214429 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.2561. Min Act: -0.0000

Data Index: 589807 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.3812. Min Act: -0.0000

Data Index: 202295 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.2121. Min Act: -0.0000

Data Index: 1247555 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1553. Min Act: -0.0000

Data Index: 668234 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1287. Min Act: -0.0000

Data Index: 772658 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1355. Min Act: -0.0000

Data Index: 583344 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.0967. Min Act: -0.0000

Data Index: 719755 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.1038. Min Act: -0.0000

Data Index: 1154426 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 4.2123. Min Range: -4.2123

Max Act: 3.0993. Min Act: -0.0000

Data Index: 605259 (C4 (Web Text))

Max Activating Token Index: 489