Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1699 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0001

Data Index: 130069 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1323619 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0518. Min Act: -0.0002

Data Index: 778811 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0502. Min Act: -0.0001

Data Index: 489318 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0497. Min Act: -0.0002

Data Index: 146651 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0493. Min Act: -0.0001

Data Index: 1045615 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0492. Min Act: -0.0002

Data Index: 935296 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0489. Min Act: -0.0002

Data Index: 913037 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0475. Min Act: -0.0002

Data Index: 744530 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0486. Min Act: -0.0001

Data Index: 637341 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0459. Min Act: -0.0002

Data Index: 92099 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1031192 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0465. Min Act: -0.0000

Data Index: 21435 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1053911 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0454. Min Act: -0.0002

Data Index: 859628 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1272175 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0457. Min Act: -0.0002

Data Index: 659026 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0455. Min Act: -0.0002

Data Index: 579793 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0457. Min Act: -0.0002

Data Index: 192681 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1090982 (C4 (Web Text))

Max Activating Token Index: 67