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

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

Neuron 1412 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: 0.0533. Min Range: -0.0533

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1191871 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1020898 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0480. Min Act: -0.0002

Data Index: 986183 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0486. Min Act: -0.0002

Data Index: 483092 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0481. Min Act: -0.0002

Data Index: 580443 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0479. Min Act: -0.0002

Data Index: 695864 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0474. Min Act: -0.0002

Data Index: 36032 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0471. Min Act: -0.0002

Data Index: 739706 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1221163 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0480. Min Act: -0.0002

Data Index: 185513 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0471. Min Act: -0.0002

Data Index: 74140 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0469. Min Act: -0.0002

Data Index: 171565 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0428. Min Act: -0.0002

Data Index: 723705 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0443. Min Act: -0.0002

Data Index: 23974 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1067893 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0428. Min Act: -0.0002

Data Index: 3919 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0437. Min Act: -0.0002

Data Index: 740353 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0437. Min Act: -0.0002

Data Index: 974907 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0439. Min Act: -0.0002

Data Index: 779837 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0422. Min Act: -0.0002

Data Index: 339599 (C4 (Web Text))

Max Activating Token Index: 504