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

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

Neuron 2067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0141. Min Act: -0.0001

Data Index: 1577843 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0940. Min Act: -0.0001

Data Index: 1567673 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5807. Min Act: -0.0001

Data Index: 1511250 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.7702. Min Act: -0.0000

Data Index: 1437760 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.7615. Min Act: -0.0001

Data Index: 1508048 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5362. Min Act: -0.0000

Data Index: 1527700 (Python Code)

Max Activating Token Index: 318

Text #6

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.4118. Min Act: -0.0001

Data Index: 1647260 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.8277. Min Act: -0.0000

Data Index: 1646011 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5044. Min Act: -0.0000

Data Index: 1366433 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5982. Min Act: -0.0000

Data Index: 1539378 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.3947. Min Act: -0.0001

Data Index: 1496186 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.4106. Min Act: -0.0000

Data Index: 1475746 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5596. Min Act: -0.0000

Data Index: 1537635 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5898. Min Act: -0.0001

Data Index: 1532100 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.4741. Min Act: -0.0000

Data Index: 1549312 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.1922. Min Act: -0.0001

Data Index: 1602377 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5642. Min Act: -0.0001

Data Index: 1653653 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.2919. Min Act: -0.0000

Data Index: 1558402 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.5625. Min Act: -0.0000

Data Index: 1558968 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.4092. Min Act: -0.0001

Data Index: 1481747 (Python Code)

Max Activating Token Index: 889