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

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

Neuron 156 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: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0001

Data Index: 151334 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0505. Min Act: -0.0001

Data Index: 114830 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0494. Min Act: -0.0001

Data Index: 451811 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0468. Min Act: -0.0001

Data Index: 329478 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0476. Min Act: -0.0000

Data Index: 964084 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0482. Min Act: -0.0001

Data Index: 730275 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0470. Min Act: -0.0001

Data Index: 324532 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0443. Min Act: -0.0001

Data Index: 872185 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0438. Min Act: -0.0002

Data Index: 696472 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0438. Min Act: -0.0002

Data Index: 851806 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0452. Min Act: -0.0001

Data Index: 31153 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0447. Min Act: -0.0001

Data Index: 545467 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0434. Min Act: -0.0001

Data Index: 545151 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0425. Min Act: -0.0001

Data Index: 192009 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0427. Min Act: -0.0001

Data Index: 679610 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0438. Min Act: -0.0001

Data Index: 978804 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0425. Min Act: -0.0001

Data Index: 975314 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0435. Min Act: -0.0001

Data Index: 706484 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0403. Min Act: -0.0001

Data Index: 246555 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0433. Min Act: -0.0002

Data Index: 774309 (C4 (Web Text))

Max Activating Token Index: 489