Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1256788 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0588. Min Act: -0.0001

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0604. Min Act: -0.0001

Data Index: 484333 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0618. Min Act: -0.0001

Data Index: 751452 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0490. Min Act: -0.0001

Data Index: 397439 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0569. Min Act: -0.0001

Data Index: 230945 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1018579 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0545. Min Act: -0.0001

Data Index: 62724 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0567. Min Act: -0.0001

Data Index: 446263 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0508. Min Act: -0.0001

Data Index: 449244 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0615. Min Act: -0.0001

Data Index: 740281 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1140275 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0530. Min Act: -0.0001

Data Index: 376328 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0489. Min Act: -0.0001

Data Index: 50519 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0489. Min Act: -0.0001

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0484. Min Act: -0.0001

Data Index: 911698 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0471. Min Act: -0.0001

Data Index: 340508 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0476. Min Act: -0.0001

Data Index: 241376 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0477. Min Act: -0.0001

Data Index: 830470 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0488. Min Act: -0.0001

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 534