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

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

Neuron 5203 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: 3.5832. Min Range: -3.5832

Max Act: 3.5832. Min Act: -0.0000

Data Index: 186827 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4732. Min Act: -0.0000

Data Index: 496470 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.0938. Min Act: -0.0000

Data Index: 1001702 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.1534. Min Act: -0.0000

Data Index: 1229951 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.9973. Min Act: -0.0000

Data Index: 795125 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.2103. Min Act: -0.0000

Data Index: 1168408 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.0606. Min Act: -0.0000

Data Index: 1072657 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.0062. Min Act: -0.0001

Data Index: 1176111 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.9245. Min Act: -0.0001

Data Index: 212284 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.8928. Min Act: -0.0000

Data Index: 970515 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.8687. Min Act: -0.0000

Data Index: 1272209 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.7088. Min Act: -0.0000

Data Index: 83351 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.9564. Min Act: -0.0001

Data Index: 429857 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.7320. Min Act: -0.0001

Data Index: 1105051 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.7533. Min Act: -0.0000

Data Index: 35283 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.6114. Min Act: -0.0000

Data Index: 605485 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.6944. Min Act: -0.0000

Data Index: 831582 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.6886. Min Act: -0.0000

Data Index: 293127 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.6386. Min Act: -0.0000

Data Index: 535675 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 3.5832. Min Range: -3.5832

Max Act: 2.6333. Min Act: -0.0000

Data Index: 1067433 (C4 (Web Text))

Max Activating Token Index: 152