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

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

Neuron 3772 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: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0000

Data Index: 392757 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1608. Min Act: -0.0000

Data Index: 406191 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1331873 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1611. Min Act: -0.0000

Data Index: 766902 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1463. Min Act: -0.0000

Data Index: 163128 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1375. Min Act: -0.0000

Data Index: 637777 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1284090 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1323. Min Act: -0.0000

Data Index: 626661 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1332. Min Act: -0.0000

Data Index: 187699 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1345. Min Act: -0.0000

Data Index: 281696 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1392. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1622455 (Python Code)

Max Activating Token Index: 833

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1305. Min Act: -0.0000

Data Index: 74858 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1301204 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1272. Min Act: -0.0000

Data Index: 955891 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1035129 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1253. Min Act: -0.0000

Data Index: 386684 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1202. Min Act: -0.0000

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1232. Min Act: -0.0000

Data Index: 754756 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1183. Min Act: -0.0000

Data Index: 96951 (C4 (Web Text))

Max Activating Token Index: 204