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

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

Neuron 3721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1688. Min Act: -0.0000

Data Index: 572844 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1666. Min Act: -0.0000

Data Index: 119094 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1065739 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1456. Min Act: -0.0000

Data Index: 372277 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1094275 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1136007 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1065957 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1413. Min Act: -0.0000

Data Index: 869131 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1301916 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1306. Min Act: -0.0000

Data Index: 38654 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1293. Min Act: -0.0000

Data Index: 172229 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1304. Min Act: -0.0000

Data Index: 468757 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1276. Min Act: -0.0000

Data Index: 967744 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1305. Min Act: -0.0000

Data Index: 884872 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1242. Min Act: -0.0000

Data Index: 623035 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1245. Min Act: -0.0000

Data Index: 137217 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1226. Min Act: -0.0000

Data Index: 678277 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1226. Min Act: -0.0000

Data Index: 308524 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1219. Min Act: -0.0000

Data Index: 150503 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1210. Min Act: -0.0000

Data Index: 298995 (C4 (Web Text))

Max Activating Token Index: 797