Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0001

Data Index: 958175 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1693. Min Act: -0.0001

Data Index: 8103 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1611. Min Act: -0.0001

Data Index: 322982 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1631. Min Act: -0.0001

Data Index: 848127 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1596. Min Act: -0.0001

Data Index: 241299 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1501. Min Act: -0.0001

Data Index: 608431 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1534. Min Act: -0.0001

Data Index: 845182 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1462. Min Act: -0.0001

Data Index: 717063 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1193850 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1407. Min Act: -0.0001

Data Index: 698785 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1044832 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1528. Min Act: -0.0001

Data Index: 64395 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1167275 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1113913 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1046161 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1442. Min Act: -0.0001

Data Index: 452881 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1335430 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1381. Min Act: -0.0001

Data Index: 631686 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1428. Min Act: -0.0001

Data Index: 387719 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1474. Min Act: -0.0001

Data Index: 814557 (C4 (Web Text))

Max Activating Token Index: 133