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

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

Neuron 2656 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: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0003

Data Index: 676560 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0502. Min Act: -0.0003

Data Index: 347741 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0471. Min Act: -0.0003

Data Index: 957395 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0481. Min Act: -0.0003

Data Index: 723457 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1097122 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0466. Min Act: -0.0003

Data Index: 684710 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0447. Min Act: -0.0003

Data Index: 274129 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0454. Min Act: -0.0003

Data Index: 68182 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0452. Min Act: -0.0003

Data Index: 211390 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0453. Min Act: -0.0004

Data Index: 688484 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0465. Min Act: -0.0003

Data Index: 673307 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0451. Min Act: -0.0004

Data Index: 1032517 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1460932 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0429. Min Act: -0.0003

Data Index: 24814 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0436. Min Act: -0.0003

Data Index: 743494 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0469. Min Act: -0.0003

Data Index: 647290 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0441. Min Act: -0.0003

Data Index: 351888 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0445. Min Act: -0.0004

Data Index: 761084 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1205887 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0460. Min Act: -0.0004

Data Index: 853668 (C4 (Web Text))

Max Activating Token Index: 422