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

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

Neuron 4356 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0003

Data Index: 415025 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1088177 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0523. Min Act: -0.0003

Data Index: 504502 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0504. Min Act: -0.0003

Data Index: 106661 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0497. Min Act: -0.0003

Data Index: 534995 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1279474 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1300566 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1274919 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1315824 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0483. Min Act: -0.0003

Data Index: 203727 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0458. Min Act: -0.0003

Data Index: 315113 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0489. Min Act: -0.0003

Data Index: 811163 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0460. Min Act: -0.0003

Data Index: 369350 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0471. Min Act: -0.0003

Data Index: 21790 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0456. Min Act: -0.0003

Data Index: 398409 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1273875 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0469. Min Act: -0.0003

Data Index: 775108 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0458. Min Act: -0.0003

Data Index: 487657 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1190924 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0449. Min Act: -0.0003

Data Index: 222652 (C4 (Web Text))

Max Activating Token Index: 444