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

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

Neuron 372 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1543343 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1534779 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1592207 (Python Code)

Max Activating Token Index: 475

Text #3

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5863. Min Act: -0.0001

Data Index: 1563182 (Python Code)

Max Activating Token Index: 329

Text #4

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1603925 (Python Code)

Max Activating Token Index: 796

Text #5

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1505531 (Python Code)

Max Activating Token Index: 538

Text #6

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4501. Min Act: -0.0001

Data Index: 1561606 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4823. Min Act: -0.0001

Data Index: 1505626 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4914. Min Act: -0.0001

Data Index: 1634055 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1380131 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1649364 (Python Code)

Max Activating Token Index: 161

Text #11

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4643. Min Act: -0.0001

Data Index: 1646747 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4327. Min Act: -0.0001

Data Index: 1472073 (Python Code)

Max Activating Token Index: 983

Text #13

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1450592 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4963. Min Act: -0.0001

Data Index: 1489234 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1362020 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4455. Min Act: -0.0001

Data Index: 1474673 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4842. Min Act: -0.0001

Data Index: 1647517 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4522. Min Act: -0.0001

Data Index: 1369761 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4487. Min Act: -0.0001

Data Index: 1502632 (Python Code)

Max Activating Token Index: 846