Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1800 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0004

Data Index: 1349673 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0429. Min Act: -0.0004

Data Index: 940029 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0417. Min Act: -0.0005

Data Index: 68031 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0408. Min Act: -0.0004

Data Index: 53187 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0393. Min Act: -0.0004

Data Index: 77342 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0378. Min Act: -0.0004

Data Index: 171264 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1330874 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0369. Min Act: -0.0004

Data Index: 185254 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0376. Min Act: -0.0004

Data Index: 1153153 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0368. Min Act: -0.0004

Data Index: 44383 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0367. Min Act: -0.0005

Data Index: 2795 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0373. Min Act: -0.0004

Data Index: 540431 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0372. Min Act: -0.0004

Data Index: 630998 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0365. Min Act: -0.0005

Data Index: 1153537 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1076969 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0363. Min Act: -0.0004

Data Index: 435432 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0353. Min Act: -0.0004

Data Index: 783997 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0360. Min Act: -0.0005

Data Index: 1090630 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0353. Min Act: -0.0004

Data Index: 252564 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0352. Min Act: -0.0004

Data Index: 669372 (C4 (Web Text))

Max Activating Token Index: 41