Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 795 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0001

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1131299 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0521. Min Act: -0.0001

Data Index: 511708 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0505. Min Act: -0.0001

Data Index: 387839 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0411. Min Act: -0.0001

Data Index: 384033 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0329. Min Act: -0.0001

Data Index: 13388 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0361. Min Act: -0.0001

Data Index: 278632 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1332039 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0330. Min Act: -0.0001

Data Index: 7934 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1006740 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0345. Min Act: -0.0001

Data Index: 940161 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0336. Min Act: -0.0001

Data Index: 714079 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0316. Min Act: -0.0001

Data Index: 933139 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1444178 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0348. Min Act: -0.0001

Data Index: 366379 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1423877 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1366881 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1568840 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1497149 (Python Code)

Max Activating Token Index: 823

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1530031 (Python Code)

Max Activating Token Index: 828