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

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

Neuron 1838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1791. Min Range: -3.1791

Max Act: 3.1791. Min Act: -0.0001

Data Index: 970637 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.8836. Min Act: -0.0001

Data Index: 94663 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.6520. Min Act: -0.0001

Data Index: 1081779 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.7804. Min Act: -0.0001

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.6467. Min Act: -0.0001

Data Index: 624808 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.4260. Min Act: -0.0001

Data Index: 215638 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.7535. Min Act: -0.0001

Data Index: 1220377 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.5775. Min Act: -0.0001

Data Index: 441019 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.4800. Min Act: -0.0001

Data Index: 1109078 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.6650. Min Act: -0.0001

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.3214. Min Act: -0.0001

Data Index: 880454 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.4248. Min Act: -0.0001

Data Index: 1153825 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.6223. Min Act: -0.0001

Data Index: 813054 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.0857. Min Act: -0.0001

Data Index: 325644 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.5697. Min Act: -0.0001

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.3372. Min Act: -0.0001

Data Index: 296627 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.2083. Min Act: -0.0001

Data Index: 1177426 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.3257. Min Act: -0.0001

Data Index: 93046 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.4506. Min Act: -0.0001

Data Index: 474209 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 3.1791. Min Range: -3.1791

Max Act: 2.0739. Min Act: -0.0001

Data Index: 503734 (C4 (Web Text))

Max Activating Token Index: 758