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

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

Neuron 30 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2694. Min Range: -2.2694

Max Act: 2.2694. Min Act: -0.0000

Data Index: 1520714 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.9894. Min Act: -0.0000

Data Index: 1643419 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1368830 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1641350 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1501468 (Python Code)

Max Activating Token Index: 894

Text #5

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1490851 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1420309 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1361841 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1430264 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1528975 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1475593 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1435604 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1567312 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1444022 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1426028 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1402606 (Python Code)

Max Activating Token Index: 465

Text #16

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1473176 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1617459 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.3743. Min Act: -0.0000

Data Index: 1478938 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 2.2694. Min Range: -2.2694

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1518488 (Python Code)

Max Activating Token Index: 640