Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 976 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.5846. Min Act: -0.0000

Data Index: 1491378 (Python Code)

Max Activating Token Index: 283

Text #1

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.5392. Min Act: -0.0000

Data Index: 1473612 (Python Code)

Max Activating Token Index: 267

Text #2

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.4057. Min Act: -0.0000

Data Index: 1589494 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2584. Min Act: -0.0000

Data Index: 1443943 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.1987. Min Act: -0.0000

Data Index: 1394758 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2920. Min Act: -0.0000

Data Index: 1589525 (Python Code)

Max Activating Token Index: 265

Text #6

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2092. Min Act: -0.0000

Data Index: 1469495 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.0853. Min Act: -0.0000

Data Index: 1501502 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1449702 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.1441. Min Act: -0.0000

Data Index: 1642221 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.1506. Min Act: -0.0000

Data Index: 1438342 (Python Code)

Max Activating Token Index: 682

Text #11

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2558. Min Act: -0.0000

Data Index: 1360575 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.1181. Min Act: -0.0000

Data Index: 1614165 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2008. Min Act: -0.0000

Data Index: 1440992 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.3286. Min Act: -0.0000

Data Index: 1516935 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.1908. Min Act: -0.0000

Data Index: 1623474 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9655. Min Act: -0.0000

Data Index: 1450633 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9574. Min Act: -0.0000

Data Index: 1572717 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9366. Min Act: -0.0000

Data Index: 1513602 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.0504. Min Act: -0.0000

Data Index: 1418410 (Python Code)

Max Activating Token Index: 38