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

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

Neuron 5682 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3621. Min Act: -0.0002

Data Index: 1552791 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3076. Min Act: -0.0002

Data Index: 1470566 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3139. Min Act: -0.0002

Data Index: 1401834 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3046. Min Act: -0.0002

Data Index: 1591474 (Python Code)

Max Activating Token Index: 315

Text #4

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3044. Min Act: -0.0002

Data Index: 1550835 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3021. Min Act: -0.0002

Data Index: 1538513 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3012. Min Act: -0.0002

Data Index: 1430661 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2963. Min Act: -0.0002

Data Index: 1554520 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2951. Min Act: -0.0002

Data Index: 1474277 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2976. Min Act: -0.0002

Data Index: 1445650 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3006. Min Act: -0.0002

Data Index: 1646929 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2917. Min Act: -0.0002

Data Index: 1476787 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2939. Min Act: -0.0002

Data Index: 1380578 (Python Code)

Max Activating Token Index: 476

Text #13

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2912. Min Act: -0.0002

Data Index: 1596810 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2905. Min Act: -0.0002

Data Index: 1379573 (Python Code)

Max Activating Token Index: 577

Text #15

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2924. Min Act: -0.0002

Data Index: 1519092 (Python Code)

Max Activating Token Index: 440

Text #16

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2898. Min Act: -0.0002

Data Index: 1527170 (Python Code)

Max Activating Token Index: 519

Text #17

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2871. Min Act: -0.0002

Data Index: 1496573 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2885. Min Act: -0.0002

Data Index: 1563747 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2877. Min Act: -0.0002

Data Index: 1413610 (Python Code)

Max Activating Token Index: 374