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

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

Neuron 1151 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0001

Data Index: 245437 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0604. Min Act: -0.0001

Data Index: 900228 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0580. Min Act: -0.0001

Data Index: 666156 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0574. Min Act: -0.0001

Data Index: 468640 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1201402 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0512. Min Act: -0.0001

Data Index: 247320 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0563. Min Act: -0.0001

Data Index: 298493 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1059349 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0506. Min Act: -0.0001

Data Index: 4906 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0505. Min Act: -0.0001

Data Index: 236646 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0502. Min Act: -0.0001

Data Index: 943368 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0492. Min Act: -0.0001

Data Index: 101764 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0494. Min Act: -0.0001

Data Index: 56138 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0511. Min Act: -0.0001

Data Index: 962445 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0505. Min Act: -0.0001

Data Index: 852128 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0495. Min Act: -0.0001

Data Index: 635612 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1166581 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0507. Min Act: -0.0001

Data Index: 47228 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1097030 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0469. Min Act: -0.0001

Data Index: 996642 (C4 (Web Text))

Max Activating Token Index: 292