Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0552. Min Act: -0.0003

Data Index: 319934 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0501. Min Act: -0.0003

Data Index: 260697 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0531. Min Act: -0.0003

Data Index: 726459 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0492. Min Act: -0.0003

Data Index: 863758 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0484. Min Act: -0.0003

Data Index: 29120 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0475. Min Act: -0.0003

Data Index: 533536 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0484. Min Act: -0.0003

Data Index: 377766 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0490. Min Act: -0.0003

Data Index: 270628 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0463. Min Act: -0.0003

Data Index: 860366 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0488. Min Act: -0.0003

Data Index: 868997 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0473. Min Act: -0.0003

Data Index: 909326 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0470. Min Act: -0.0004

Data Index: 786821 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0475. Min Act: -0.0003

Data Index: 17571 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0453. Min Act: -0.0003

Data Index: 829513 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0445. Min Act: -0.0003

Data Index: 95084 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0437. Min Act: -0.0003

Data Index: 313637 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0454. Min Act: -0.0003

Data Index: 425321 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0436. Min Act: -0.0003

Data Index: 188730 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1161149 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0450. Min Act: -0.0003

Data Index: 302506 (C4 (Web Text))

Max Activating Token Index: 320