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

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

Neuron 118 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: 0.0700. Min Range: -0.0700

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1504802 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1649623 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1516616 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1493124 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1446062 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1627224 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1397618 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1555676 (Python Code)

Max Activating Token Index: 53

Text #8

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1386018 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1579453 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1601622 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1644957 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1482042 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1399887 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1601768 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1427637 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1615821 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1640194 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1431298 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1537657 (Python Code)

Max Activating Token Index: 50