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

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

Neuron 3436 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1776. Min Act: -0.0000

Data Index: 124237 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1609. Min Act: -0.0000

Data Index: 992795 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1672. Min Act: -0.0000

Data Index: 239745 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1152181 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1601. Min Act: -0.0000

Data Index: 172428 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1127707 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1646. Min Act: -0.0000

Data Index: 438040 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1331687 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1315178 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1341 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1497. Min Act: -0.0000

Data Index: 232873 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1455. Min Act: -0.0000

Data Index: 440426 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1600. Min Act: -0.0000

Data Index: 769248 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1545. Min Act: -0.0000

Data Index: 312289 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1485. Min Act: -0.0000

Data Index: 53993 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1506. Min Act: -0.0000

Data Index: 516727 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1457. Min Act: -0.0000

Data Index: 261512 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1548. Min Act: -0.0000

Data Index: 447521 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1299937 (C4 (Web Text))

Max Activating Token Index: 577