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

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

Neuron 3123 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.9516. Min Act: -0.0000

Data Index: 578370 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1335585 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.8572. Min Act: -0.0000

Data Index: 409933 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7801. Min Act: -0.0000

Data Index: 617207 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1129342 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.7426. Min Act: -0.0000

Data Index: 450878 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6369. Min Act: -0.0000

Data Index: 922047 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1049841 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6830. Min Act: -0.0000

Data Index: 117539 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6758. Min Act: -0.0000

Data Index: 461470 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6313. Min Act: -0.0000

Data Index: 904159 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6199. Min Act: -0.0000

Data Index: 250070 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.6129. Min Act: -0.0000

Data Index: 852036 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5549. Min Act: -0.0000

Data Index: 316764 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1001072 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5950. Min Act: -0.0000

Data Index: 321374 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5642. Min Act: -0.0000

Data Index: 740876 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1107709 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5613. Min Act: -0.0000

Data Index: 450650 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.9554. Min Range: -0.9554

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1342338 (C4 (Web Text))

Max Activating Token Index: 489