Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5992 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0001

Data Index: 791106 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0620. Min Act: -0.0001

Data Index: 2383 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0565. Min Act: -0.0001

Data Index: 928225 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0546. Min Act: -0.0001

Data Index: 567289 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0460. Min Act: -0.0001

Data Index: 929799 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0470. Min Act: -0.0001

Data Index: 838342 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0432. Min Act: -0.0001

Data Index: 359079 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0489. Min Act: -0.0001

Data Index: 151621 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0448. Min Act: -0.0001

Data Index: 50197 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0420. Min Act: -0.0001

Data Index: 624502 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0457. Min Act: -0.0001

Data Index: 924036 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0465. Min Act: -0.0001

Data Index: 697140 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1048146 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0441. Min Act: -0.0001

Data Index: 11516 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0423. Min Act: -0.0001

Data Index: 781888 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0438. Min Act: -0.0001

Data Index: 439475 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0424. Min Act: -0.0001

Data Index: 221364 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0465. Min Act: -0.0001

Data Index: 936727 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1352072 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0440. Min Act: -0.0001

Data Index: 253630 (C4 (Web Text))

Max Activating Token Index: 165