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

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

Neuron 3803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.3416. Min Act: -0.0000

Data Index: 908058 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.3183. Min Act: -0.0000

Data Index: 726261 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.3093. Min Act: -0.0000

Data Index: 553170 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2973. Min Act: -0.0000

Data Index: 309016 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2887. Min Act: 0.0000

Data Index: 223538 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1253261 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2833. Min Act: 0.0000

Data Index: 198303 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2558. Min Act: 0.0000

Data Index: 1025061 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2467. Min Act: -0.0000

Data Index: 978975 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2458. Min Act: 0.0000

Data Index: 266290 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2513. Min Act: -0.0000

Data Index: 688373 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2419. Min Act: -0.0000

Data Index: 526929 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2332. Min Act: -0.0000

Data Index: 384624 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2210. Min Act: -0.0000

Data Index: 754348 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2265. Min Act: -0.0000

Data Index: 516598 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2248. Min Act: 0.0000

Data Index: 603082 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2215. Min Act: -0.0000

Data Index: 393386 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2192. Min Act: -0.0000

Data Index: 886450 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2121. Min Act: -0.0000

Data Index: 740671 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.3416. Min Range: -0.3416

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1051844 (C4 (Web Text))

Max Activating Token Index: 374