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

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

Neuron 830 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: 0.0530. Min Act: -0.0002

Data Index: 1195333 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0002

Data Index: 244701 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0509. Min Act: -0.0002

Data Index: 989102 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0504. Min Act: -0.0002

Data Index: 787555 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0496. Min Act: -0.0002

Data Index: 744366 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0482. Min Act: -0.0002

Data Index: 985219 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0473. Min Act: -0.0002

Data Index: 935141 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0473. Min Act: -0.0002

Data Index: 618526 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0485. Min Act: -0.0002

Data Index: 322364 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0479. Min Act: -0.0002

Data Index: 320348 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0467. Min Act: -0.0002

Data Index: 948402 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0482. Min Act: -0.0002

Data Index: 950235 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1305016 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0470. Min Act: -0.0002

Data Index: 925554 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0484. Min Act: -0.0002

Data Index: 527661 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0483. Min Act: -0.0002

Data Index: 923751 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0456. Min Act: -0.0002

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0473. Min Act: -0.0002

Data Index: 757029 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0480. Min Act: -0.0002

Data Index: 94866 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0471. Min Act: -0.0002

Data Index: 679058 (C4 (Web Text))

Max Activating Token Index: 353