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

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

Neuron 1526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1154154 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5719. Min Act: -0.0000

Data Index: 809512 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5541. Min Act: -0.0000

Data Index: 641181 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.5033. Min Act: -0.0000

Data Index: 715581 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1297263 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4546. Min Act: -0.0000

Data Index: 362950 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4533. Min Act: -0.0000

Data Index: 678258 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4382. Min Act: -0.0000

Data Index: 578058 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4270. Min Act: -0.0000

Data Index: 949572 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4681. Min Act: -0.0000

Data Index: 328035 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4272. Min Act: -0.0000

Data Index: 110539 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1112183 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1361487 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4488. Min Act: -0.0000

Data Index: 878276 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1459366 (Python Code)

Max Activating Token Index: 327

Text #15

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4647. Min Act: -0.0000

Data Index: 642614 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4122. Min Act: -0.0000

Data Index: 711725 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1399829 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4223. Min Act: -0.0000

Data Index: 994791 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.6456. Min Range: -0.6456

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1565234 (Python Code)

Max Activating Token Index: 453