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

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

Neuron 3727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0000

Data Index: 853369 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1122303 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1648879 (Python Code)

Max Activating Token Index: 286

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0531. Min Act: -0.0000

Data Index: 416438 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0563. Min Act: -0.0000

Data Index: 694347 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0502. Min Act: 0.0000

Data Index: 147281 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1168156 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0490. Min Act: -0.0000

Data Index: 803889 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0504. Min Act: -0.0000

Data Index: 519848 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0504. Min Act: -0.0000

Data Index: 599115 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0509. Min Act: 0.0000

Data Index: 38703 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0471. Min Act: -0.0000

Data Index: 708026 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0497. Min Act: -0.0000

Data Index: 676241 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0449. Min Act: -0.0000

Data Index: 398195 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0464. Min Act: -0.0000

Data Index: 73085 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0479. Min Act: -0.0000

Data Index: 622371 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0458. Min Act: -0.0000

Data Index: 686689 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0464. Min Act: -0.0000

Data Index: 432614 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1003713 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0429. Min Act: -0.0000

Data Index: 78944 (C4 (Web Text))

Max Activating Token Index: 343