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

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

Neuron 4285 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3806. Min Act: -0.0000

Data Index: 996787 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3708. Min Act: -0.0000

Data Index: 687354 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1601320 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1307670 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1412862 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2777. Min Act: -0.0000

Data Index: 894948 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3026. Min Act: -0.0000

Data Index: 102732 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1544592 (Python Code)

Max Activating Token Index: 326

Text #8

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2772. Min Act: -0.0000

Data Index: 974380 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1680. Min Act: -0.0000

Data Index: 749730 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1221890 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1459. Min Act: -0.0000

Data Index: 406042 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1018311 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1532677 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1493. Min Act: -0.0000

Data Index: 106822 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1294854 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1364417 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2085. Min Act: -0.0000

Data Index: 114248 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1226. Min Act: -0.0000

Data Index: 190942 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1572434 (Python Code)

Max Activating Token Index: 302