Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 785 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0006

Data Index: 827459 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0497. Min Act: -0.0006

Data Index: 1277495 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0485. Min Act: -0.0006

Data Index: 883290 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0496. Min Act: -0.0006

Data Index: 121210 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0476. Min Act: -0.0006

Data Index: 92079 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0481. Min Act: -0.0006

Data Index: 758612 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0492. Min Act: -0.0006

Data Index: 114351 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0480. Min Act: -0.0006

Data Index: 96746 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0477. Min Act: -0.0006

Data Index: 529903 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0474. Min Act: -0.0006

Data Index: 1146510 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0453. Min Act: -0.0006

Data Index: 329358 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0487. Min Act: -0.0006

Data Index: 189808 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0447. Min Act: -0.0006

Data Index: 547114 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0451. Min Act: -0.0006

Data Index: 41440 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0498. Min Act: -0.0006

Data Index: 926652 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0437. Min Act: -0.0006

Data Index: 1188011 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0436. Min Act: -0.0006

Data Index: 647748 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0433. Min Act: -0.0006

Data Index: 873316 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0436. Min Act: -0.0006

Data Index: 394305 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0426. Min Act: -0.0006

Data Index: 1099576 (C4 (Web Text))

Max Activating Token Index: 366