Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 446282 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1212560 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0548. Min Act: -0.0002

Data Index: 38679 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1103749 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0547. Min Act: -0.0002

Data Index: 886195 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0467. Min Act: -0.0002

Data Index: 186994 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0537. Min Act: -0.0002

Data Index: 439384 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0399. Min Act: -0.0002

Data Index: 588516 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1086105 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0570. Min Act: -0.0002

Data Index: 492025 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0511. Min Act: -0.0002

Data Index: 134793 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1286421 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0424. Min Act: -0.0002

Data Index: 484178 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0428. Min Act: -0.0002

Data Index: 436846 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0492. Min Act: -0.0002

Data Index: 86758 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1330301 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1269453 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0423. Min Act: -0.0002

Data Index: 238978 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1324347 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0464. Min Act: -0.0002

Data Index: 857676 (C4 (Web Text))

Max Activating Token Index: 761