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

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

Neuron 4538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1688. Min Act: -0.0000

Data Index: 453292 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1550123 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.0373. Min Act: -0.0000

Data Index: 117616 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1544079 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1589455 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1350823 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1581802 (Python Code)

Max Activating Token Index: 409

Text #7

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1379053 (Python Code)

Max Activating Token Index: 713

Text #8

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1615619 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 1.1688. Min Range: -1.1688

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1568504 (Python Code)

Max Activating Token Index: 194

Text #10

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.7139. Min Act: -0.0000

Data Index: 274802 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.8538. Min Act: -0.0000

Data Index: 730851 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1405634 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1408644 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1610222 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1439961 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1503964 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1585760 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1415577 (Python Code)

Max Activating Token Index: 160

Text #19

Max Range: 1.1688. Min Range: -1.1688

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1385823 (Python Code)

Max Activating Token Index: 742