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

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

Neuron 3084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.6825. Min Act: -0.0001

Data Index: 1593920 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.6485. Min Act: -0.0001

Data Index: 1609524 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4620. Min Act: -0.0001

Data Index: 1436606 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.6507. Min Act: -0.0001

Data Index: 1507491 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.5747. Min Act: -0.0001

Data Index: 1445486 (Python Code)

Max Activating Token Index: 97

Text #5

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3354. Min Act: -0.0001

Data Index: 1532815 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4832. Min Act: -0.0001

Data Index: 1527234 (Python Code)

Max Activating Token Index: 717

Text #7

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4180. Min Act: -0.0001

Data Index: 1455128 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4546. Min Act: -0.0001

Data Index: 1554014 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4391. Min Act: -0.0001

Data Index: 1525454 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4253. Min Act: -0.0001

Data Index: 1504932 (Python Code)

Max Activating Token Index: 324

Text #11

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3798. Min Act: -0.0001

Data Index: 1517126 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3322. Min Act: -0.0001

Data Index: 1452059 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.2883. Min Act: -0.0001

Data Index: 1614392 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.4224. Min Act: -0.0001

Data Index: 1524225 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3881. Min Act: -0.0001

Data Index: 1359939 (Python Code)

Max Activating Token Index: 557

Text #16

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3255. Min Act: -0.0001

Data Index: 1378312 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3420. Min Act: -0.0001

Data Index: 1397791 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3348. Min Act: -0.0001

Data Index: 1648978 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 1.6825. Min Range: -1.6825

Max Act: 1.3145. Min Act: -0.0001

Data Index: 1361258 (Python Code)

Max Activating Token Index: 9