Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0005

Data Index: 375720 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1703. Min Act: -0.0005

Data Index: 1101026 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1497. Min Act: -0.0005

Data Index: 1159356 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1556. Min Act: -0.0005

Data Index: 512132 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1548. Min Act: -0.0005

Data Index: 675599 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1481. Min Act: -0.0005

Data Index: 7499 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1402. Min Act: -0.0005

Data Index: 134120 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1349. Min Act: -0.0005

Data Index: 522371 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1384. Min Act: -0.0005

Data Index: 290826 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1353. Min Act: -0.0005

Data Index: 989841 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1350. Min Act: -0.0005

Data Index: 1195473 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1277. Min Act: -0.0005

Data Index: 1065091 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1330. Min Act: -0.0005

Data Index: 419239 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1329. Min Act: -0.0005

Data Index: 87319 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1377. Min Act: -0.0005

Data Index: 826251 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1331. Min Act: -0.0005

Data Index: 718618 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1321. Min Act: -0.0005

Data Index: 1064430 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1216. Min Act: -0.0005

Data Index: 811769 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1320. Min Act: -0.0005

Data Index: 474586 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1300. Min Act: -0.0005

Data Index: 558418 (C4 (Web Text))

Max Activating Token Index: 252