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

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

Neuron 510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 588312 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0490. Min Act: -0.0002

Data Index: 636994 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0492. Min Act: -0.0002

Data Index: 994428 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0466. Min Act: -0.0002

Data Index: 811343 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1264563 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0455. Min Act: -0.0002

Data Index: 936725 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1253379 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1174829 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0463. Min Act: -0.0002

Data Index: 479839 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1651 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0443. Min Act: -0.0002

Data Index: 233974 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0454. Min Act: -0.0002

Data Index: 16442 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0453. Min Act: -0.0002

Data Index: 261603 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0460. Min Act: -0.0002

Data Index: 718382 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0444. Min Act: -0.0002

Data Index: 57606 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0438. Min Act: -0.0002

Data Index: 818380 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0451. Min Act: -0.0002

Data Index: 997454 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0446. Min Act: -0.0002

Data Index: 54466 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0440. Min Act: -0.0002

Data Index: 787609 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1341136 (C4 (Web Text))

Max Activating Token Index: 155