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

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

Neuron 4933 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2356. Min Range: -4.2356

Max Act: 4.2356. Min Act: -0.0000

Data Index: 1639318 (Python Code)

Max Activating Token Index: 818

Text #1

Max Range: 4.2356. Min Range: -4.2356

Max Act: 4.2139. Min Act: -0.0000

Data Index: 1490014 (Python Code)

Max Activating Token Index: 888

Text #2

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.2993. Min Act: -0.0000

Data Index: 1467891 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.3933. Min Act: -0.0000

Data Index: 1422177 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.3835. Min Act: -0.0000

Data Index: 1544940 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.3224. Min Act: -0.0000

Data Index: 1620877 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.2794. Min Act: -0.0000

Data Index: 1501238 (Python Code)

Max Activating Token Index: 181

Text #7

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.2808. Min Act: -0.0000

Data Index: 1656312 (Python Code)

Max Activating Token Index: 579

Text #8

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.2506. Min Act: -0.0000

Data Index: 1542274 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.4270. Min Act: -0.0000

Data Index: 1624737 (Python Code)

Max Activating Token Index: 229

Text #10

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.2098. Min Act: -0.0000

Data Index: 1365819 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1826. Min Act: -0.0000

Data Index: 1610790 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1836. Min Act: -0.0000

Data Index: 1590875 (Python Code)

Max Activating Token Index: 650

Text #13

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.0141. Min Act: -0.0000

Data Index: 1431737 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.8886. Min Act: -0.0000

Data Index: 1401635 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.2135. Min Act: -0.0000

Data Index: 1621228 (Python Code)

Max Activating Token Index: 719

Text #16

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.0866. Min Act: -0.0000

Data Index: 1582867 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.0943. Min Act: -0.0000

Data Index: 1529937 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1935. Min Act: -0.0000

Data Index: 16705 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1929. Min Act: -0.0000

Data Index: 1586683 (Python Code)

Max Activating Token Index: 551