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

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

Neuron 4806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0522. Min Range: -3.0522

Max Act: 3.0522. Min Act: -0.0000

Data Index: 1645248 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.9375. Min Act: -0.0000

Data Index: 47024 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.0522. Min Range: -3.0522

Max Act: 3.0480. Min Act: -0.0000

Data Index: 1589660 (Python Code)

Max Activating Token Index: 688

Text #3

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.6404. Min Act: -0.0000

Data Index: 1418695 (Python Code)

Max Activating Token Index: 845

Text #4

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.8539. Min Act: -0.0000

Data Index: 1393833 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.9062. Min Act: -0.0000

Data Index: 1504756 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.6934. Min Act: -0.0000

Data Index: 1454379 (Python Code)

Max Activating Token Index: 222

Text #7

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.6438. Min Act: -0.0000

Data Index: 1554753 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.3577. Min Act: -0.0000

Data Index: 1550500 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.4791. Min Act: -0.0000

Data Index: 1451769 (Python Code)

Max Activating Token Index: 638

Text #10

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.4405. Min Act: -0.0000

Data Index: 1581962 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.2801. Min Act: -0.0000

Data Index: 1404839 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.2519. Min Act: -0.0000

Data Index: 341008 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.4874. Min Act: -0.0000

Data Index: 1567325 (Python Code)

Max Activating Token Index: 939

Text #14

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.3521. Min Act: -0.0000

Data Index: 1495986 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.4829. Min Act: -0.0000

Data Index: 1642583 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.4652. Min Act: -0.0000

Data Index: 1451328 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.3253. Min Act: -0.0000

Data Index: 1373290 (Python Code)

Max Activating Token Index: 738

Text #18

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.1786. Min Act: -0.0000

Data Index: 1546386 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 3.0522. Min Range: -3.0522

Max Act: 2.1641. Min Act: -0.0000

Data Index: 1555945 (Python Code)

Max Activating Token Index: 952