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

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

Neuron 2961 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1534202 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.6683. Min Act: -0.0001

Data Index: 1557809 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.6701. Min Act: -0.0001

Data Index: 1565171 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.5232. Min Act: -0.0001

Data Index: 1503124 (Python Code)

Max Activating Token Index: 329

Text #4

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.4726. Min Act: -0.0001

Data Index: 1641108 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3199. Min Act: -0.0001

Data Index: 1528809 (Python Code)

Max Activating Token Index: 353

Text #6

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3059. Min Act: -0.0001

Data Index: 1452113 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1596919 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1598223 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2798. Min Act: -0.0001

Data Index: 1572601 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2777. Min Act: -0.0001

Data Index: 1583814 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1431114 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1493864 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1590725 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2133. Min Act: -0.0001

Data Index: 1486710 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3124. Min Act: -0.0001

Data Index: 1505289 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1577730 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1494. Min Act: -0.0001

Data Index: 1611181 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1407133 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2129. Min Act: -0.0001

Data Index: 1454390 (Python Code)

Max Activating Token Index: 377