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

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

Neuron 314 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0489. Min Act: -0.0002

Data Index: 253520 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0002

Data Index: 973500 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0468. Min Act: -0.0002

Data Index: 402481 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0461. Min Act: -0.0001

Data Index: 942844 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0462. Min Act: -0.0002

Data Index: 46184 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0454. Min Act: -0.0002

Data Index: 804330 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1287101 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0448. Min Act: -0.0002

Data Index: 62926 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0441. Min Act: -0.0002

Data Index: 455046 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0437. Min Act: -0.0002

Data Index: 534871 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0438. Min Act: -0.0001

Data Index: 636300 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0417. Min Act: -0.0002

Data Index: 403190 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1142488 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1328234 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0422. Min Act: -0.0002

Data Index: 286525 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0411. Min Act: -0.0002

Data Index: 925446 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1087302 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0427. Min Act: -0.0002

Data Index: 352542 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0411. Min Act: -0.0002

Data Index: 171659 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0420. Min Act: -0.0002

Data Index: 285527 (C4 (Web Text))

Max Activating Token Index: 766