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

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

Neuron 2321 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3844. Min Act: -0.0000

Data Index: 358285 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3699. Min Act: -0.0000

Data Index: 822666 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3579. Min Act: -0.0000

Data Index: 812089 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3696. Min Act: -0.0000

Data Index: 945288 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3017. Min Act: -0.0000

Data Index: 403943 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3408. Min Act: -0.0000

Data Index: 674938 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3101. Min Act: -0.0000

Data Index: 698728 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1595125 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2949. Min Act: -0.0000

Data Index: 687404 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2823. Min Act: -0.0000

Data Index: 525711 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.3040. Min Act: -0.0000

Data Index: 676113 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2993. Min Act: -0.0000

Data Index: 623397 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1083537 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2889. Min Act: -0.0000

Data Index: 211282 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2812. Min Act: -0.0000

Data Index: 275362 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2627. Min Act: -0.0000

Data Index: 359300 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2547. Min Act: -0.0000

Data Index: 226977 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1622083 (Python Code)

Max Activating Token Index: 631

Text #18

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1556619 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 0.3844. Min Range: -0.3844

Max Act: 0.2385. Min Act: -0.0000

Data Index: 654640 (C4 (Web Text))

Max Activating Token Index: 142