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

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

Neuron 3830 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1502351 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1521361 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1387147 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1458014 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1497393 (Python Code)

Max Activating Token Index: 293

Text #5

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2238. Min Act: 0.0000

Data Index: 1596007 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1550371 (Python Code)

Max Activating Token Index: 505

Text #7

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1400056 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1529667 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1431255 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1580217 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1524788 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1540660 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1463508 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1102429 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1394343 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1536373 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1714. Min Act: 0.0000

Data Index: 1447381 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1718. Min Act: 0.0003

Data Index: 1443861 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 0.3206. Min Range: -0.3206

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1612317 (Python Code)

Max Activating Token Index: 943