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

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

Neuron 2203 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3935. Min Act: -0.0002

Data Index: 1380283 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3950. Min Act: -0.0002

Data Index: 1578887 (Python Code)

Max Activating Token Index: 575

Text #2

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4228. Min Act: -0.0002

Data Index: 1404365 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4008. Min Act: -0.0002

Data Index: 1619730 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3554. Min Act: -0.0002

Data Index: 1564242 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3777. Min Act: -0.0002

Data Index: 1627302 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3817. Min Act: -0.0002

Data Index: 1610608 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3585. Min Act: -0.0002

Data Index: 1420146 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3550. Min Act: -0.0002

Data Index: 1616949 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2995. Min Act: -0.0002

Data Index: 1461113 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3578. Min Act: -0.0002

Data Index: 1604779 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3482. Min Act: -0.0002

Data Index: 1440047 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3630. Min Act: -0.0002

Data Index: 1560222 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3677. Min Act: -0.0002

Data Index: 1308009 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3308. Min Act: -0.0002

Data Index: 1456767 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3697. Min Act: -0.0002

Data Index: 1591974 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3367. Min Act: -0.0002

Data Index: 694303 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3243. Min Act: -0.0002

Data Index: 1363158 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3033. Min Act: -0.0002

Data Index: 1655616 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3737. Min Act: -0.0002

Data Index: 1539452 (Python Code)

Max Activating Token Index: 706