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

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

Neuron 2887 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0003

Data Index: 31754 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1187779 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0482. Min Act: -0.0003

Data Index: 758567 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1220216 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0471. Min Act: -0.0003

Data Index: 737077 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0449. Min Act: -0.0003

Data Index: 656526 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0477. Min Act: -0.0003

Data Index: 28337 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0463. Min Act: -0.0003

Data Index: 567396 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0462. Min Act: -0.0003

Data Index: 546607 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0459. Min Act: -0.0003

Data Index: 959904 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0455. Min Act: -0.0003

Data Index: 250911 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0501. Min Act: -0.0003

Data Index: 22918 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0452. Min Act: -0.0003

Data Index: 774587 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0470. Min Act: -0.0003

Data Index: 175142 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1002836 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1618883 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1159306 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0452. Min Act: -0.0003

Data Index: 240628 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0431. Min Act: -0.0003

Data Index: 727323 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1137960 (C4 (Web Text))

Max Activating Token Index: 887